© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66391
    Prev
    Next
    INDEX
    Explanations

    more information

    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
     most
    -1.00
     pengurus
    -0.94
     همان
    -0.93
    Xna
    -0.93
     He
    -0.91
    iveau
    -0.90
    ratislava
    -0.89
    zió
    -0.88
     a
    -0.87
     Day
    -0.86
    POSITIVE LOGITS
     about
    1.25
     regarding
    1.16
     including
    1.10
     Ajouter
    1.08
     ceket
    1.08
     Partagez
    1.04
    erobic
    1.02
     môžete
    1.01
     contactar
    1.01
    vanju
    1.00
    Activations Density 0.019%

    No Known Activations