© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47035
    Prev
    Next
    INDEX
    Explanations

    Q: question heads

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

    The neuron flags C/C++ code declarations and template syntax (e.g. struct definitions, int declarations, and map<char,int>‐style constructs).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    nades
    -0.69
     keş
    -0.68
     complementary
    -0.68
     SARA
    -0.68
    coordinate
    -0.66
    ccan
    -0.66
    UFC
    -0.66
     Paragon
    -0.66
     Boulder
    -0.65
    nent
    -0.65
    POSITIVE LOGITS
    NTT
    0.90
    
    0.81
     пъ
    0.80
    废
    0.79
    Female
    0.78
     NTT
    0.77
    إنه
    0.77
    Leonard
    0.74
    lanatory
    0.73
     défense
    0.71
    Activations Density 0.016%

    No Known Activations