© 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. 10-GEMMASCOPE-RES-131K
    7. 8479
    Prev
    Next
    INDEX
    Explanations

    Date formats or lists

    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_10/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
     better
    -1.67
     more
    -1.45
     &
    -1.45
     appear
    -1.36
     ähnliche
    -1.35
     whom
    -1.34
     to
    -1.30
    en
    -1.30
     fün
    -1.30
     best
    -1.27
    POSITIVE LOGITS
    приєм
    1.92
    cisive
    1.77
     見る
    1.62
    klart
    1.56
    初めての
    1.49
    ется
    1.45
    にほんブログ村
    1.43
    ってました
    1.40
     willen
    1.38
    //!
    1.38
    Activations Density 0.004%

    No Known Activations