© 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. 40294
    Prev
    Next
    INDEX
    Explanations

    acting as a character

    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
     जाएंगे
    0.52
    dding
    0.50
     λόγω
    0.49
    🍵
    0.49
     ძალიან
    0.47
    काळ
    0.47
    Beach
    0.46
     গাঙ্গুলির
    0.45
    एगी
    0.45
     क्योंकि
    0.45
    POSITIVE LOGITS
     bibli
    0.46
     an
    0.45
     U
    0.44
     <
    0.44
     R
    0.44
     Publishers
    0.43
     >
    0.43
     analyzed
    0.42
     preach
    0.42
     Werte
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.