© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116545
    Prev
    Next
    INDEX
    Explanations

    the following word

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

    The neuron fires on the single keyword that names the core topic of a Q/A post (e.g. the technical term or proper noun around which the question or answer revolves).

    oai_token-act-pair · o4-miniTriggered 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
    主要
    -1.07
    uding
    -1.03
    ensa
    -1.02
    osphere
    -0.98
    леге
    -0.97
    iling
    -0.95
    iam
    -0.94
    ize
    -0.94
     arsenal
    -0.92
    voer
    -0.92
    POSITIVE LOGITS
     following
    1.41
     same
    1.29
     επίσης
    1.27
     seguenti
    1.11
     aptly
    1.05
     equally
    1.05
    並不
    1.03
    安く
    0.99
    名为
    0.97
     rather
    0.96
    Activations Density 0.219%

    No Known Activations