© 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. 145162
    Prev
    Next
    INDEX
    Explanations

    virtual tours

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

    SELECT DATE_FORMAT

    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
    Commun
    0.50
    asciiPanel
    0.50
    ⮚
    0.50
     разнообраз
    0.48
     ব্যাপক
    0.48
    prits
    0.48
    FRAMERATE
    0.48
     வருக
    0.48
     इवेंट
    0.47
     rares
    0.47
    POSITIVE LOGITS
     Th
    0.45
    ен
    0.45
     Queen
    0.44
     F
    0.43
    是
    0.42
     f
    0.42
    除了
    0.42
    ع
    0.42
     Sh
    0.42
     U
    0.41
    Activations Density 0.001%

    No Known Activations