© 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. 20993
    Prev
    Next
    INDEX
    Explanations

    electricity, procedure, cancer, television, World

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

    nouns related to specialized fields or professions like medicine, law, science, and geography.

    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
     to
    -2.39
     are
    -1.52
     of
    -1.49
    amanda
    -1.39
    cristal
    -1.37
    hanno
    -1.33
    trying
    -1.32
    푘
    -1.32
    ременно
    -1.31
     peines
    -1.30
    POSITIVE LOGITS
     venit
    1.53
     and
    1.39
     colocación
    1.38
     noastre
    1.36
    هایی
    1.34
     competición
    1.34
     assistance
    1.32
     elegancia
    1.31
    asties
    1.31
     obsession
    1.30
    Activations Density 0.215%

    No Known Activations