© 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. 212204
    Prev
    Next
    INDEX
    Explanations

    animals heels

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

    labs and systems

    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
    ┑
    0.54
     gimnaz
    0.50
    剱
    0.50
    сову
    0.48
     설명을
    0.48
     했던
    0.47
    CCIÓN
    0.46
    йо
    0.46
    뷸
    0.46
    dol
    0.45
    POSITIVE LOGITS
    of
    0.44
     Queens
    0.43
     of
    0.42
     Behind
    0.42
     mist
    0.41
     Restricted
    0.40
     restrict
    0.39
     Infected
    0.38
    佉
    0.38
     Mist
    0.38
    Activations Density 0.000%

    No Known Activations