© 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. 85288
    Prev
    Next
    INDEX
    Explanations

    cleaning instructions or specifications

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

    information, documentation, or effects

    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
     pressed
    0.47
    тах
    0.47
     ยัง
    0.46
     frayed
    0.46
    ’:
    0.46
    tted
    0.46
     car
    0.45
     Scand
    0.44
     employees
    0.44
    `:
    0.44
    POSITIVE LOGITS
    К
    0.63
    Werk
    0.59
    现在
    0.57
    Questo
    0.57
    淚
    0.56
    あ
    0.56
    إن
    0.55
    Depuis
    0.55
    Этот
    0.54
    Now
    0.53
    Activations Density 0.000%

    No Known Activations