© 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. 3253
    Prev
    Next
    INDEX
    Explanations

    broken down

    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
    batas
    -0.83
     medir
    -0.79
     cenu
    -0.77
    righted
    -0.77
     many
    -0.75
     jí
    -0.74
    jdzie
    -0.73
    waża
    -0.73
    𝟚
    -0.72
    criteria
    -0.71
    POSITIVE LOGITS
     breakdown
    5.22
     Breakdown
    4.16
    breakdown
    4.06
    Breakdown
    3.83
     breakdowns
    3.70
     break
    2.66
     breakup
    2.63
     desglose
    2.47
     BREAK
    2.31
    Break
    2.20
    Activations Density 0.056%

    No Known Activations