© 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. 73052
    Prev
    Next
    INDEX
    Explanations

    time zones or poems

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

    sequence followed by delimiter

    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
    ı
    0.50
    Laz
    0.49
    Rank
    0.48
    Echo
    0.48
    Harper
    0.48
     kolo
    0.48
    Alchemy
    0.47
    Meta
    0.47
     overrun
    0.46
    Counts
    0.46
    POSITIVE LOGITS
     同じ
    0.59
     cytokines
    0.55
     동일
    0.52
     設計
    0.50
     cytokine
    0.50
     動
    0.50
     為
    0.49
     ต
    0.49
     আলোচিত
    0.49
     fhe
    0.47
    Activations Density 0.000%

    No Known Activations