© 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. 62350
    Prev
    Next
    INDEX
    Explanations

    Minerals, vitamins, medical marijuana

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

    apps and lists

    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
    资源的
    0.44
     reaf
    0.43
     ܡ
    0.43
     tener
    0.42
    grant
    0.42
    .`);
    0.41
     മാർ
    0.41
    鑾
    0.41
     conced
    0.41
    ());
    0.41
    POSITIVE LOGITS
    вши
    0.55
    น
    0.48
    ة
    0.47
     Бел
    0.46
    ной
    0.45
    न
    0.45
    erus
    0.45
    oblig
    0.43
    інки
    0.42
    нский
    0.42
    Activations Density 0.000%

    No Known Activations