© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112113
    Prev
    Next
    INDEX
    Explanations

    representation, origins, services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    is
    0.45
    i
    0.45
    ’
    0.43
    hur
    0.42
     Approved
    0.42
     irresist
    0.41
     approved
    0.41
    ARE
    0.40
    ONG
    0.40
    Approved
    0.40
    POSITIVE LOGITS
    Ᏺ
    0.45
    和服务
    0.44
     এতটা
    0.43
     बढ़ना
    0.43
     diting
    0.43
     میلیون
    0.43
     खींचो
    0.42
    தந்திர
    0.42
     এতটাই
    0.42
    ુદ્ધ
    0.42
    Activations Density 0.006%

    No Known Activations