© 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. 10-GEMMASCOPE-RES-131K
    7. 59236
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms

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

    This neuron responds to unusually rare or domain-specific tokens (e.g. long punctuation runs, proper names, non-English characters, technical terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鷙
    -3.22
    酲
    -3.22
     撮り
    -3.14
    
    -3.00
    媖
    -2.98
    𓆏
    -2.97
     炖
    -2.97
    婼
    -2.89
    黼
    -2.88
    ‪.‬‬
    -2.84
    POSITIVE LOGITS
    ↵
    4.88
    {
    3.92
     --
    3.34
    ?
    3.06
    f
    3.06
    3
    3.03
    =
    2.88
     NOT
    2.80
    ),
    2.78
    or
    2.77
    Activations Density 0.028%

    No Known Activations