© 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. 63042
    Prev
    Next
    INDEX
    Explanations

    Japanese text and coding structure

    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
     Championship
    -0.75
     Infected
    -0.72
    gestaltung
    -0.72
     infected
    -0.71
     addiction
    -0.70
     serum
    -0.70
    şk
    -0.70
     zile
    -0.69
     combinaison
    -0.69
     championship
    -0.68
    POSITIVE LOGITS
     Smash
    0.95
    Smash
    0.85
     pertence
    0.76
    चाल
    0.75
     lämp
    0.75
     yazı
    0.75
    助
    0.74
     以上
    0.73
    mii
    0.72
     stalo
    0.71
    Activations Density 0.017%

    No Known Activations