© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20963
    Prev
    Next
    INDEX
    Explanations

    toururu website paths

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

    programming languages and AI services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ї
    0.46
    magnitude
    0.44
    Gamb
    0.44
    erdas
    0.41
     тоді
    0.41
    alignment
    0.41
    thi
    0.40
    ď
    0.40
    orbit
    0.40
    gahan
    0.40
    POSITIVE LOGITS
     productId
    0.55
     producto
    0.49
     alguna
    0.48
     Laravel
    0.48
     Día
    0.48
     Gemma
    0.47
     específ
    0.47
     Expr
    0.46
     Produkten
    0.46
     Some
    0.46
    Activations Density 0.000%

    No Known Activations