© 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. 129131
    Prev
    Next
    INDEX
    Explanations

    strong impact or effect

    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
    ease
    -1.54
    (
    -1.41
     maravillosas
    -1.41
     it
    -1.39
     hvordan
    -1.37
     あり
    -1.36
     preciosas
    -1.31
    Ꮵ
    -1.27
    lış
    -1.27
    cluye
    -1.27
    POSITIVE LOGITS
     is
    1.73
    derdag
    1.52
    }{*}{}
    1.52
    からお
    1.51
    萣
    1.44
    uegos
    1.43
    volezza
    1.43
     "
    1.37
    ↵↵↵↵
    1.34
    Bromoform
    1.34
    Activations Density 0.021%

    No Known Activations