© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107538
    Prev
    Next
    INDEX
    Explanations

    code generation or file headers

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

    The neuron fires on code that calls MATLAB’s Excel‐export function (i.e. detects the “xlswrite” call).

    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
     Ode
    -0.82
     Vial
    -0.81
    Modul
    -0.74
    +"/"+
    -0.73
     Antioch
    -0.73
     Grims
    -0.73
    par
    -0.72
    möglichen
    -0.71
    figure
    -0.69
     Meier
    -0.69
    POSITIVE LOGITS
    fid
    0.95
     fid
    0.87
    nrows
    0.81
    lizard
    0.74
     Persönlichkeit
    0.73
    怖い
    0.73
     }}$.
    0.73
     iff
    0.72
     tehdä
    0.72
    дження
    0.71
    Activations Density 0.012%

    No Known Activations