© 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. 110978
    Prev
    Next
    INDEX
    Explanations

    CGI script

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

    proper nouns that are names of places, organizations, or specific technical terms (like "Bloomsbury", "BARNETT", "CGI", "Pathfinder", "CET").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ୌ
    -2.95
    鋱
    -2.94
     seier
    -2.89
     egen
    -2.78
     cabeza
    -2.77
     необходи
    -2.73
     millioner
    -2.67
    荩
    -2.67
     enthou
    -2.66
    s
    -2.66
    POSITIVE LOGITS
    er
    3.03
    *
    3.02
    </strong>
    2.95
     Roughly
    2.75
     hidupnya
    2.69
    но
    2.66
     lamented
    2.61
     of
    2.59
    {
    2.56
    е
    2.56
    Activations Density 0.098%

    No Known Activations