© 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. 57238
    Prev
    Next
    INDEX
    Explanations

    code comment headers

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

    The neuron fires on numeric tokens (digit sequences), i.e. any standalone 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
     even
    -1.24
     in
    -1.13
     Even
    -1.04
    したもの
    -1.04
     this
    -1.02
     on
    -1.02
    Even
    -0.97
     nacional
    -0.91
     даже
    -0.90
     people
    -0.89
    POSITIVE LOGITS
     \
    2.06
    \
    1.63
     \
    1.41
    }\
    1.38
    ..\..\
    1.12
     verhind
    1.09
     "\
    1.05
    ]\
    1.05
     ทำ
    1.01
     @
    0.97
    Activations Density 0.011%

    No Known Activations