© 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. 11144
    Prev
    Next
    INDEX
    Explanations

    trading, casino, book, car, list

    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
    bewerken
    -1.30
     Ausdrücke
    -1.12
    beitet
    -1.10
    UCIÓN
    -1.09
     Bearbeitung
    -1.07
    chaqueta
    -1.03
     Riproduzione
    -1.02
    gration
    -1.02
     Begriffe
    -1.01
    devtool
    -1.01
    POSITIVE LOGITS
    '
    1.16
    -
    1.15
    に入れる
    1.15
    or
    1.14
     damski
    1.11
     cérami
    1.09
     noires
    1.08
    (
    1.05
     Mère
    1.03
    あぁ
    1.02
    Activations Density 0.002%

    No Known Activations