© 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. 99316
    Prev
    Next
    INDEX
    Explanations

    this.accessor

    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
     for
    -2.30
     that
    -2.08
     of
    -2.03
     thinks
    -1.87
     ambayo
    -1.85
    、“
    -1.84
     which
    -1.83
    на
    -1.77
     believes
    -1.68
     from
    -1.65
    POSITIVE LOGITS
    鉏
    2.45
    {
    2.22
    泚
    1.97
    nargs
    1.89
    ſche
    1.88
    
    1.80
    詎
    1.78
    ሖ
    1.77
    {...
    1.75
    %
    1.72
    Activations Density 0.006%

    No Known Activations