© 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. 75422
    Prev
    Next
    INDEX
    Explanations

    Please note

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

    project management discussion points

    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
     miała
    0.56
     habían
    0.51
     Elemente
    0.50
     liée
    0.50
    ą
    0.50
    ные
    0.48
     ayudará
    0.48
     tint
    0.47
     narzęd
    0.47
     miał
    0.47
    POSITIVE LOGITS
    MAK
    0.52
    。「
    0.48
    がございます
    0.47
    GRAM
    0.47
    BUR
    0.45
    冖
    0.44
    RENDITION
    0.44
    iddel
    0.44
    戒指
    0.44
    dem
    0.43
    Activations Density 0.001%

    No Known Activations