© 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. 73640
    Prev
    Next
    INDEX
    Explanations

    piece of

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

    piece of X

    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
    </strong>
    0.80
    e
    0.78
    a
    0.75
    u
    0.72
    o
    0.71
    G
    0.69
    F
    0.68
    ↵
    0.68
    S
    0.66
    ish
    0.63
    POSITIVE LOGITS
     قطعة
    1.14
     кусо
    1.10
     टुकड़े
    0.96
     pieces
    0.94
    一块
    0.89
     片
    0.84
     pieza
    0.83
     pezzi
    0.80
    片段
    0.79
     morceaux
    0.79
    Activations Density 0.301%

    No Known Activations