© 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. 23899
    Prev
    Next
    INDEX
    Explanations

    claim your blog

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

    Entities working, interactive courses

    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
    و
    0.55
    OL
    0.53
     banknote
    0.51
     byproduct
    0.47
    O
    0.47
    G
    0.47
    ωνα
    0.46
    Ο
    0.46
     milion
    0.46
    לו
    0.45
    POSITIVE LOGITS
    getPath
    0.50
     うん
    0.49
     एलर्जी
    0.49
     ادي
    0.48
     Dés
    0.48
    徝
    0.47
     पढ़ाने
    0.47
     техника
    0.47
     உண்ண
    0.47
    âteaux
    0.46
    Activations Density 0.000%

    No Known Activations