© 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. 41929
    Prev
    Next
    INDEX
    Explanations

    beta-catenin signaling,OCT, ECDSA

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

    scientific or technical terms, particularly related to molecular biology (like "beta-catenin") and technology (like "OCT" and "ecdsa").

    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
     A
    -2.44
     An
    -2.19
     In
    -2.08
     It
    -1.97
     Of
    -1.95
     the
    -1.89
     At
    -1.82
     is
    -1.78
     in
    -1.74
     If
    -1.70
    POSITIVE LOGITS
     havaianas
    1.82
     vode
    1.77
    莇
    1.70
    鮃
    1.67
    鯪
    1.66
     kask
    1.65
     masaj
    1.65
     ragaz
    1.64
    ⃢
    1.64
     boya
    1.63
    Activations Density 0.137%

    No Known Activations