© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39526
    Prev
    Next
    INDEX
    Explanations

    "query" delimited phrases

    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
    ম
    0.49
     ND
    0.47
     ail
    0.46
     कलम
    0.45
     サイド
    0.45
    ASTER
    0.45
    ITI
    0.45
     молоко
    0.45
     あ
    0.45
    אס
    0.45
    POSITIVE LOGITS
    եք
    0.46
    ுகளை
    0.45
    glichkeiten
    0.45
     অভিন
    0.43
    ப்பும்
    0.42
    一篇
    0.42
    ுகளில்
    0.41
    тый
    0.41
     novoProduto
    0.41
    cü
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.