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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26104
    Prev
    Next
    INDEX
    Explanations

    farm, alive, indefinitely, fossils

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

    sentences or phrases that describe physical characteristics or conditions of objects.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron sharply activates on content-bearing words (nouns, verbs, adjectives, etc.) and stays quiescent on common function words and punctuation.

    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
     dát
    -1.78
     trám
    -1.73
     Légion
    -1.69
    很赞
    -1.58
     разных
    -1.56
    傒
    -1.53
    숑
    -1.52
    甗
    -1.52
     нынеш
    -1.51
     erhi
    -1.50
    POSITIVE LOGITS
     as
    2.22
     in
    1.95
     at
    1.82
     While
    1.68
     on
    1.63
     In
    1.52
     Often
    1.52
     often
    1.50
     if
    1.49
     over
    1.48
    Activations Density 0.422%

    No Known Activations