© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150126
    Prev
    Next
    INDEX
    Explanations

    participation and requests

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

    various contexts

    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
     versucht
    0.47
     بيت
    0.46
     quelque
    0.46
     similit
    0.46
    Tre
    0.45
     belirli
    0.45
    Hashing
    0.45
    욤
    0.45
    物語
    0.45
    Nell
    0.44
    POSITIVE LOGITS
    inas
    0.50
    im
    0.49
    od
    0.49
    iar
    0.49
    lasting
    0.49
    ang
    0.47
    iß
    0.45
    rums
    0.45
    µ
    0.44
    ys
    0.44
    Activations Density 0.000%

    No Known Activations