© 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. 66243
    Prev
    Next
    INDEX
    Explanations

    take action or make a choice

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

    specific details and requirements

    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
    ጇ
    0.50
     изменя
    0.49
    пот
    0.48
    ྛ
    0.47
     використову
    0.46
    堃
    0.46
    ст
    0.46
     ஈடுப
    0.46
     více
    0.46
    兹
    0.46
    POSITIVE LOGITS
     تاکہ
    0.47
     sanitary
    0.46
     national
    0.45
    ensure
    0.45
     courthouse
    0.45
    national
    0.44
    เพื่อให้
    0.44
     supaya
    0.44
     (!)
    0.44
     deadlines
    0.43
    Activations Density 0.003%

    No Known Activations