© 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. 27560
    Prev
    Next
    INDEX
    Explanations

    special phrases or names

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

    professionalism and requests

    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
    ass
    0.47
    wert
    0.46
     $-\
    0.46
    ↵↵
    0.45
     contributors
    0.45
     ปก
    0.45
    ﹔
    0.44
     intermedia
    0.43
     SCAN
    0.43
     intern
    0.43
    POSITIVE LOGITS
     Greedy
    0.47
    鸵
    0.47
    龴
    0.47
     Drops
    0.46
    ક્ર
    0.46
     diosa
    0.46
     Dro
    0.45
    Dropdown
    0.43
     منك
    0.43
    总经理
    0.43
    Activations Density 0.000%

    No Known Activations