© 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. 10-GEMMASCOPE-RES-131K
    7. 128104
    Prev
    Next
    INDEX
    Explanations

    double discharge, double-blind, double-ended

    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_10/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
    .
    -2.81
    ↵↵
    -1.95
    {
    -1.93
     
    -1.78
    dersfield
    -1.70
    )
    -1.64
     The
    -1.63
    𞤤
    -1.59
     Wim
    -1.49
     ultimi
    -1.48
    POSITIVE LOGITS
    and
    2.13
     και
    1.87
    ayaquil
    1.82
     и
    1.80
    áculo
    1.77
     şi
    1.76
    และ
    1.72
     और
    1.72
     và
    1.71
     our
    1.70
    Activations Density 0.027%

    No Known Activations