© 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. 144227
    Prev
    Next
    INDEX
    Explanations

    record, saving, guarantee

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

    address components and names

    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
    Negative Logits
    м
    0.54
     jestem
    0.50
    ้ว
    0.49
     серде
    0.49
    ็
    0.49
    ายเป็น
    0.47
    лений
    0.47
    मनी
    0.46
     brinda
    0.46
    ำ
    0.45
    POSITIVE LOGITS
     الكسور
    0.47
     ઝડ
    0.45
     Mexico
    0.43
     rectangles
    0.43
    xRt
    0.43
    雹
    0.42
     аласыз
    0.42
    RenderTarget
    0.42
    首先
    0.41
    Px
    0.41
    Activations Density 0.000%

    No Known Activations