© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 70084
    Prev
    Next
    INDEX
    Explanations

    operations or activities

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on content-bearing words (nouns, verbs, adjectives, and adverbs) rather than on function words or punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words or phrases related to formal or technical contexts, such as legal documents, official policies, and structured descriptions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    phrases indicating operational status, options, or service/logistics details within formal informational or administrative text.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nerv
    -0.84
    ceptos
    -0.81
    enneth
    -0.78
    throwaway
    -0.76
     Visibility
    -0.75
    Dilution
    -0.74
    iS
    -0.74
    aryana
    -0.71
    راز
    -0.70
    hamdulillah
    -0.70
    POSITIVE LOGITS
     indoor
    1.19
     outdoor
    1.01
    customer
    0.97
    limited
    0.91
     indoors
    0.88
    tetés
    0.85
    seller
    0.85
     operate
    0.84
    train
    0.83
    limit
    0.83
    Activations Density 0.001%

    No Known Activations