© 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. 34-GEMMASCOPE-RES-131K
    7. 78215
    Prev
    Next
    INDEX
    Explanations

    code licenses

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

    This neuron is strongly activated by numeric tokens (digits and numbers) in the text.

    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
    例文帳に追加
    -0.97
     sveta
    -0.81
     girl
    -0.75
     sred
    -0.74
    står
    -0.74
    Steg
    -0.73
    这一切
    -0.72
    AuthContext
    -0.72
     prosperous
    -0.72
     ann
    -0.72
    POSITIVE LOGITS
     Xs
    0.84
    द्ध
    0.84
     秘密
    0.82
     FSM
    0.82
     "")
    0.82
     demnach
    0.80
    @[+][
    0.80
     @"
    0.79
    mô
    0.77
    Infinity
    0.76
    Activations Density 0.004%

    No Known Activations