© 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. 22-GEMMASCOPE-RES-131K
    4. 10912
    Prev
    Next
    INDEX
    Explanations

    items, places, and activities

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

    The neuron strongly activates on relatively rare, content‐heavy nouns and proper nouns (long or specialized terms rather than common function words).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    3
    -0.98
     DevComponents
    -0.97
    gencies
    -0.87
    ütt
    -0.87
    O
    -0.86
    0
    -0.85
    了一会儿
    -0.84
     вони
    -0.84
    скус
    -0.84
    dzie
    -0.83
    POSITIVE LOGITS
    вь
    0.94
    fmf
    0.93
     \%}$
    0.93
    ificada
    0.90
     desmotiv
    0.90
    岖
    0.90
    僕も
    0.90
    specially
    0.90
    𝑫
    0.89
    などの
    0.88
    Activations Density 0.199%

    No Known Activations