© 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. 22-GEMMASCOPE-RES-131K
    7. 25288
    Prev
    Next
    INDEX
    Explanations

    introducing examples

    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_22/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
     that
    -1.59
     only
    -1.27
     života
    -1.23
     жовтня
    -1.18
     because
    -1.18
     then
    -1.16
     to
    -1.09
    出来た
    -1.09
     только
    -1.07
     when
    -1.05
    POSITIVE LOGITS
     such
    2.81
     including
    2.23
    比如
    1.96
     таких
    1.91
    such
    1.77
    例如
    1.76
     namely
    1.75
     такие
    1.75
     например
    1.67
    Including
    1.67
    Activations Density 0.043%

    No Known Activations