© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110457
    Prev
    Next
    INDEX
    Explanations

    restricted help glutathione

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

    XML and code syntax elements like attributes, namespace declarations, and programming language symbols.

    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_34/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
     CVS
    -0.73
    kö
    -0.72
    ugget
    -0.71
    Tomorrow
    -0.70
     Köl
    -0.68
     ਨੂੰ
    -0.67
     IBM
    -0.65
    modern
    -0.65
    imoto
    -0.65
    ész
    -0.64
    POSITIVE LOGITS
     $\|
    0.82
     $|\
    0.72
     piggy
    0.68
    zeichnis
    0.67
    uments
    0.67
     uniforms
    0.66
     consta
    0.66
     Bassi
    0.65
     Cek
    0.64
     Directors
    0.63
    Activations Density 0.050%

    No Known Activations