© 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. 117142
    Prev
    Next
    INDEX
    Explanations

    drivers, admitted to

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Totals
    -0.83
    Reliability
    -0.78
    サギ
    -0.72
    Bandit
    -0.71
     Reliability
    -0.70
    ดด
    -0.68
    期刊论文
    -0.67
     coté
    -0.67
     dba
    -0.66
     Dred
    -0.66
    POSITIVE LOGITS
    Amit
    0.77
    getOutputStream
    0.73
     Amit
    0.72
     সং
    0.70
     Tam
    0.69
    Columbus
    0.69
    amboo
    0.68
     Plat
    0.66
     Celsius
    0.66
    復
    0.66
    Activations Density 0.062%

    No Known Activations