© 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. 128359
    Prev
    Next
    INDEX
    Explanations

    modifying or extending existing things

    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
    谆
    -1.21
     pomá
    -1.14
    Смотрите
    -1.07
    齣
    -1.06
    тут
    -1.05
     dernières
    -1.04
    大約
    -1.03
    很難
    -1.01
    認真
    -1.01
    Эзо
    -1.01
    POSITIVE LOGITS
     to
    2.19
     existing
    2.13
     the
    2.02
    existing
    1.49
     our
    1.34
     it
    1.32
     previous
    1.30
     bestaande
    1.30
     your
    1.29
     существу
    1.28
    Activations Density 0.086%

    No Known Activations