© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48651
    Prev
    Next
    INDEX
    Explanations

    fighter names and fights

    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
     спеціаль
    -0.85
    baix
    -0.77
     independence
    -0.77
     wollt
    -0.77
    httpMethod
    -0.76
     swiftly
    -0.73
    antro
    -0.73
     low
    -0.73
     his
    -0.73
     race
    -0.72
    POSITIVE LOGITS
    Į
    0.88
    fight
    0.88
     thai
    0.87
     ALTO
    0.85
     SECON
    0.83
    ܆
    0.83
    MMA
    0.83
    sao
    0.81
    ׳
    0.81
    fights
    0.81
    Activations Density 0.023%

    No Known Activations