© 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. 100923
    Prev
    Next
    INDEX
    Explanations

    responsibility shall

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

    enable faster

    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
    龛
    0.52
    詆
    0.51
    国务院
    0.50
    簡易
    0.50
    酚
    0.50
    協會
    0.49
    出典
    0.48
    ам
    0.47
    দিগের
    0.47
    هان
    0.47
    POSITIVE LOGITS
    poque
    0.45
    hoti
    0.43
     Burnu
    0.43
    ‌
    0.43
    rakk
    0.43
     краї
    0.42
    ztat
    0.42
     ooz
    0.42
     Nge
    0.42
     ذلك
    0.41
    Activations Density 0.001%

    No Known Activations