© 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. 124010
    Prev
    Next
    INDEX
    Explanations

    common words followed by common words

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

    code repositories

    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
    出现
    0.48
    Em
    0.48
     Em
    0.45
     erscheint
    0.45
     erscheinen
    0.44
     Ezek
    0.44
    ఈ
    0.43
    म
    0.42
     quadrilateral
    0.42
     कराई
    0.42
    POSITIVE LOGITS
    Ttest
    0.49
     pô
    0.45
    adil
    0.45
    セラ
    0.45
    iles
    0.44
    êtes
    0.44
    đồng
    0.44
    ancellation
    0.44
     моде
    0.43
     গে
    0.42
    Activations Density 0.000%

    No Known Activations