© 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. 68187
    Prev
    Next
    INDEX
    Explanations

    `this.` followed by method/variable

    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
     when
    -2.05
     on
    -1.73
     because
    -1.73
     for
    -1.72
     During
    -1.71
     numerosas
    -1.68
     would
    -1.64
     numerous
    -1.61
     that
    -1.59
     should
    -1.54
    POSITIVE LOGITS
     gena
    1.73
     siè
    1.63
     apporter
    1.59
     citroen
    1.55
     stiefel
    1.52
    despite
    1.46
     ´
    1.45
    <em>
    1.45
     trug
    1.45
     rezept
    1.45
    Activations Density 0.003%

    No Known Activations