© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69590
    Prev
    Next
    INDEX
    Explanations

    Trout beck, man, et, stream, chow, rivers

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "trout" in various contexts related to the fish species.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     主要
    -2.70
    F
    -2.67
    A
    -2.55
    C
    -2.53
     vorigen
    -2.48
     Gegensatz
    -2.45
    For
    -2.42
    On
    -2.38
     Our
    -2.27
    U
    -2.27
    POSITIVE LOGITS
    塒
    2.91
     they
    2.80
    i
    2.77
     ouvido
    2.63
    髕
    2.52
     speichern
    2.48
    懨
    2.48
    тке
    2.47
     embarked
    2.44
    筇
    2.44
    Activations Density 0.007%

    No Known Activations