© 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. 48296
    Prev
    Next
    INDEX
    Explanations

    ability, memes, departments, Browns

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

    income generation monetize existing

    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
     pancreatic
    0.48
    全
    0.48
    agt
    0.47
     पूरी
    0.44
    ichen
    0.44
    Ẽ
    0.44
     केंद्रों
    0.43
    armos
    0.43
    osiery
    0.43
    veless
    0.42
    POSITIVE LOGITS
    า
    0.54
    ಾ
    0.47
    ้าว
    0.45
     zapewn
    0.45
    ้า
    0.44
    дава
    0.44
    똥
    0.44
    ائع
    0.44
     прибыли
    0.44
     irony
    0.42
    Activations Density 0.000%

    No Known Activations