© 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. 189757
    Prev
    Next
    INDEX
    Explanations

    brandishes, dollars, willing to

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

    roles and context

    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
    on
    0.53
    Rich
    0.52
    Medical
    0.52
    Disk
    0.49
    생
    0.49
    Vid
    0.49
    abilities
    0.48
    Cone
    0.47
    Value
    0.47
    Let
    0.47
    POSITIVE LOGITS
     kawasan
    0.51
     intención
    0.50
     Kardashian
    0.50
     川
    0.49
    לית
    0.49
     श्याम
    0.48
     Resolución
    0.47
     ຮ
    0.46
     町
    0.46
     JAC
    0.46
    Activations Density 0.000%

    No Known Activations