© 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. 206213
    Prev
    Next
    INDEX
    Explanations

    numbers, industries, instructor, tourism

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

    fake nail developers AI

    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
    设计
    0.50
    副
    0.48
    設計
    0.48
    デザイン
    0.47
     focus
    0.47
     ডিজাই
    0.47
    那
    0.47
     като
    0.46
    ড
    0.46
     navigated
    0.45
    POSITIVE LOGITS
    ine
    0.50
     Administ
    0.47
    ėti
    0.47
     Tatum
    0.46
    otherm
    0.46
     spasms
    0.44
    amyl
    0.44
    lių
    0.44
     Volta
    0.44
    certain
    0.44
    Activations Density 0.001%

    No Known Activations