© 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. 111602
    Prev
    Next
    INDEX
    Explanations

    legal consumption of alcoholic beverage

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

    social media videos

    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
    死的
    0.53
    死了
    0.52
     Spectacular
    0.51
    false
    0.45
    reqParams
    0.44
    ।
    0.44
    的最大
    0.43
    とお
    0.43
    beau
    0.43
    DEFAULT
    0.42
    POSITIVE LOGITS
    વ
    0.51
     sends
    0.48
    в
    0.48
     ouvido
    0.46
     yere
    0.45
    പ
    0.45
     supplying
    0.44
    urat
    0.44
     ovat
    0.44
     chy
    0.44
    Activations Density 0.001%

    No Known Activations