© 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. 116299
    Prev
    Next
    INDEX
    Explanations

    way of, job done, variety of

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

    The neuron strongly activates on numeric tokens (numbers).

    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
    +"/"+
    -0.98
    centerTitle
    -0.91
    Everyone
    -0.88
     extenso
    -0.88
    //}
    -0.87
    本日
    -0.86
     Ár
    -0.86
    %，
    -0.84
     män
    -0.83
    Always
    -0.82
    POSITIVE LOGITS
    oczes
    1.12
     &
    0.98
    ceous
    0.94
    creens
    0.90
    GRP
    0.85
    tissa
    0.84
    ud
    0.83
     Franse
    0.82
     sorgfältig
    0.81
    la
    0.81
    Activations Density 0.011%

    No Known Activations