© 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. 173316
    Prev
    Next
    INDEX
    Explanations

    addition, custom, built, vinyl, aero, bereavement

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

    standardized presentation

    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
    0.49
     partnership
    0.47
     Divider
    0.46
     fr
    0.46
     Conversation
    0.45
     to
    0.45
     computation
    0.44
     ۱
    0.43
     RC
    0.43
     MSc
    0.43
    POSITIVE LOGITS
     কারণে
    0.50
    ти
    0.48
    斯
    0.48
    妈妈
    0.47
    壳
    0.47
    кая
    0.47
     наши
    0.46
     внутріш
    0.46
    шили
    0.46
     оско
    0.46
    Activations Density 0.000%

    No Known Activations