© 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. 190501
    Prev
    Next
    INDEX
    Explanations

    cooked smoked cauliflower mental pain fight

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

    leaves haveIncreased contactKnowledge Aboutprobability Cross-entropy

    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
    进行
    0.47
     xử
    0.46
     -
    0.45
    標
    0.45
    <0xE3>
    0.44
    动力
    0.43
     are
    0.43
    <li>
    0.42
    な
    0.41
    ：
    0.41
    POSITIVE LOGITS
     undervalued
    0.48
    gmzy
    0.46
    uncia
    0.46
     egot
    0.45
    ramos
    0.44
     लोकार्
    0.44
    ಕ್ಕಿಂತ
    0.44
    ಪಟ್ಟ
    0.44
    ഽ
    0.44
     morto
    0.43
    Activations Density 0.002%

    No Known Activations