© 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. 148701
    Prev
    Next
    INDEX
    Explanations

    legal options and must defend

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

    tokens not words

    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
    ே
    0.56
    insert
    0.54
    hint
    0.53
    setHora
    0.52
    wen
    0.52
    ticket
    0.52
    w
    0.51
    á
    0.50
    ficha
    0.50
    download
    0.50
    POSITIVE LOGITS
     satisfying
    0.46
     calibrations
    0.45
     defect
    0.45
    ();//
    0.44
     classifications
    0.44
     safeguard
    0.43
     slugs
    0.43
     peacetime
    0.43
     greater
    0.43
     peanut
    0.43
    Activations Density 0.002%

    No Known Activations