© 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. 33863
    Prev
    Next
    INDEX
    Explanations

    two column matrices

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

    The neuron fires on numeric tokens (e.g. integers and decimal numbers) in the text, particularly those appearing in formulas or data values.

    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
     cozin
    -1.23
    °;
    -1.13
    /*++
    -1.12
     senhora
    -1.10
    も同じ
    -1.07
     Kindheit
    -1.06
     Unterscheidung
    -1.05
     tersebut
    -1.04
     each
    -1.03
     this
    -1.02
    POSITIVE LOGITS
     مانند
    1.09
    ｇ
    1.06
     約
    1.03
    <tbody>
    0.99
    新たに
    0.98
    unknownFields
    0.93
    Ｕ
    0.93
    绥
    0.92
     pandemi
    0.91
    ۹
    0.91
    Activations Density 0.002%

    No Known Activations