© 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. 255527
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    لی
    0.52
     ไ
    0.49
    ур
    0.49
    ли
    0.47
    وله
    0.46
    Женско
    0.45
     клас
    0.43
    кри
    0.42
    чи
    0.42
     forze
    0.42
    POSITIVE LOGITS
     मात्र
    0.49
    鬍
    0.48
    gete
    0.47
    hü
    0.47
    år
    0.46
    qualität
    0.46
     rô
    0.46
    ⴳ
    0.45
     birthdays
    0.45
     गरज
    0.44
    Activations Density 0.000%

    No Known Activations