© 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. 34-GEMMASCOPE-RES-131K
    7. 108246
    Prev
    Next
    INDEX
    Explanations

    Copyright or software licensing

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    isEqualTo
    -0.77
     Cardiac
    -0.71
     Système
    -0.65
    inator
    -0.64
    原创
    -0.64
     trompe
    -0.64
    $\%$
    -0.63
    恶魔
    -0.63
     hermano
    -0.63
     laim
    -0.63
    POSITIVE LOGITS
    ctile
    0.73
     modulation
    0.70
     después
    0.68
     Twit
    0.67
    ﻼ
    0.65
    جمعیت
    0.65
    Yoda
    0.65
     fixes
    0.65
    gebied
    0.65
    agad
    0.65
    Activations Density 0.045%

    No Known Activations