© 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. 25110
    Prev
    Next
    INDEX
    Explanations

    ISBNs, phone numbers, and codes

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

    numbers that are part of identifiers or lists

    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
    ilberger
    0.72
    ب
    0.72
     رع
    0.70
     мала
    0.68
     atteinte
    0.67
     pavil
    0.66
     variés
    0.66
    urger
    0.66
     інші
    0.66
    ilä
    0.66
    POSITIVE LOGITS
    AV
    1.02
    ри
    0.98
    AST
    0.97
    J
    0.95
    AI
    0.94
    ON
    0.93
    DE
    0.91
    OP
    0.91
    O
    0.90
    IA
    0.89
    Activations Density 0.090%

    No Known Activations