© 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. 1205
    Prev
    Next
    INDEX
    Explanations

    Repolarization

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

    underscores in JSON field names like "cell_type", "full_name", and other key-value pairs.

    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
     or
    -2.80
     what
    -2.20
     you
    -1.93
     before
    -1.92
     when
    -1.83
     how
    -1.81
     should
    -1.77
     What
    -1.77
     where
    -1.72
     because
    -1.71
    POSITIVE LOGITS
    </b>
    1.77
    cally
    1.66
    usually
    1.64
    corresponding
    1.63
    lifter
    1.62
    related
    1.61
    coupled
    1.55
    various
    1.55
    backers
    1.53
    ↵
    1.52
    Activations Density 0.005%

    No Known Activations