© 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. 25509
    Prev
    Next
    INDEX
    Explanations

    Certified Scrum, Developmental trajectories, @if

    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
     alkoh
    -1.16
     娘
    -1.12
    ;%%
    -1.09
     Scritto
    -1.07
    +=(
    -1.04
     Niveau
    -1.04
     effekt
    -1.03
     mawar
    -1.02
    paikan
    -1.02
    如何在
    -1.02
    POSITIVE LOGITS
     millennial
    1.00
    urgeon
    0.97
     rollo
    0.91
    啻
    0.91
     hourglass
    0.91
     européens
    0.89
     "*.
    0.89
    tisation
    0.88
     moron
    0.86
    erializer
    0.85
    Activations Density 0.001%

    No Known Activations