© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130584
    Prev
    Next
    INDEX
    Explanations

    lists of categories and roles

    np_acts-logits-general · gemini-2.5-flash-lite

    printing directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     T
    0.57
    ays
    0.54
    istin
    0.54
    ains
    0.52
    ą
    0.52
    ica
    0.50
    ก
    0.50
    uginosa
    0.48
    ength
    0.48
     officers
    0.48
    POSITIVE LOGITS
     pakas
    0.49
     plabic
    0.44
    ENCIAS
    0.44
     sorriso
    0.42
    {//
    0.42
     Streit
    0.42
    லிக்க
    0.41
     plante
    0.41
    SOLID
    0.41
     perceptive
    0.41
    Activations Density 0.000%

    No Known Activations