© 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. 151182
    Prev
    Next
    INDEX
    Explanations

    TV show characters and names

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

    long-term investment

    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
    DriverManager
    0.51
    **,
    0.50
    ્સ
    0.49
    }-${
    0.49
    创始人
    0.48
    㬶
    0.47
    creator
    0.46
     Specials
    0.46
     नग
    0.45
    opolymers
    0.45
    POSITIVE LOGITS
     dow
    0.58
     sker
    0.50
    জর
    0.47
    ु
    0.46
     Relatively
    0.46
     soll
    0.45
     Interim
    0.45
     sich
    0.44
     Ihr
    0.44
     maksud
    0.44
    Activations Density 0.002%

    No Known Activations