© 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. 41832
    Prev
    Next
    INDEX
    Explanations

    foreign language identifiers

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

    optional argument followed by parenthesis

    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
    is
    0.50
     shoulder
    0.49
     semicol
    0.48
    ↵↵↵↵↵↵↵↵
    0.47
    NJ
    0.46
    ↵↵↵↵↵↵
    0.45
     (
    0.45
    cent
    0.45
     blackout
    0.44
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.44
    POSITIVE LOGITS
     deut
    0.52
     үч
    0.51
     Анна
    0.50
     traslado
    0.50
     Ирина
    0.49
    理工
    0.49
     وضاحت
    0.49
     наук
    0.48
     देंगे
    0.48
     دع
    0.47
    Activations Density 0.001%

    No Known Activations