© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103274
    Prev
    Next
    INDEX
    Explanations

    NF-kappaB, sigma, lambda, gamma

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

    Greek letters used in mathematical and scientific notation.

    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
     distinctive
    -2.66
    缡
    -2.42
     говорит
    -2.41
    ↵↵
    -2.36
    明確
    -2.27
    '
    -2.25
     แต่
    -2.23
     magnificent
    -2.20
     definitive
    -2.19
     svých
    -2.19
    POSITIVE LOGITS
    which
    2.47
    стями
    2.42
     getchar
    2.33
    "",
    2.23
    ֺ
    2.22
     When
    2.20
    ጺ
    2.17
     jSON
    2.16
    Most
    2.14
    нут
    2.14
    Activations Density 0.045%

    No Known Activations