© 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. 10-GEMMASCOPE-RES-131K
    7. 120068
    Prev
    Next
    INDEX
    Explanations

    ID of

    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
     and
    -1.64
     well
    -1.62
     out
    -1.55
     also
    -1.49
     descrit
    -1.48
    ありません
    -1.47
     complicated
    -1.47
    Though
    -1.46
     tried
    -1.45
     soothing
    -1.44
    POSITIVE LOGITS
    씰
    1.64
     Actividades
    1.57
     ži
    1.55
     nació
    1.47
    klassen
    1.46
     hän
    1.46
     trám
    1.45
    produkter
    1.44
    蛲
    1.43
     realmente
    1.42
    Activations Density 0.100%

    No Known Activations