© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77277
    Prev
    Next
    INDEX
    Explanations

    version numbers and identifiers

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

    The neuron primarily detects numeric tokens (i.e. sequences of digits).

    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
    KeepAlive
    -0.77
    AutoSize
    -0.75
     舞
    -0.74
    dance
    -0.69
    bike
    -0.69
    права
    -0.68
     فور
    -0.68
    <0xD2>
    -0.68
    ciled
    -0.67
    accueil
    -0.66
    POSITIVE LOGITS
    cancelButton
    0.70
     Polyp
    0.68
    镇
    0.67
     Regen
    0.67
    Injured
    0.66
     Gug
    0.65
    ResponseModel
    0.65
     Iba
    0.63
    ggia
    0.63
     Hert
    0.63
    Activations Density 0.051%

    No Known Activations