© 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. 127991
    Prev
    Next
    INDEX
    Explanations

    acceptance or sets

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

    install apps, guilt, apt

    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
    りたい
    0.46
     figlio
    0.46
    lingu
    0.45
     diligent
    0.45
    гене
    0.45
    ेशन
    0.45
     approximating
    0.45
    У
    0.43
    сора
    0.43
    🔵
    0.43
    POSITIVE LOGITS
     पाता
    0.53
     Comercial
    0.50
     Photo
    0.50
     Shorts
    0.49
     Generalized
    0.49
     पाती
    0.48
    ki
    0.48
     Fundamentals
    0.47
     Exotic
    0.46
    čko
    0.46
    Activations Density 0.000%

    No Known Activations