© 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. 65401
    Prev
    Next
    INDEX
    Explanations

    book list introduction vehicles Q

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

    The neuron specializes in spotting tokens that contain digits (i.e. numeric substrings or identifiers with 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_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
     for
    -1.80
     all
    -1.78
    leine
    -1.73
    訛
    -1.59
     or
    -1.59
     ideen
    -1.58
    langkah
    -1.57
    
    -1.55
     in
    -1.55
    licitations
    -1.46
    POSITIVE LOGITS
    轳
    1.91
    縢
    1.73
     ‐
    1.71
     peuvent
    1.69
     entw
    1.66
    刄
    1.66
     languid
    1.62
     turmoil
    1.62
    ⏑
    1.61
     famed
    1.59
    Activations Density 0.000%

    No Known Activations