© 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. 66400
    Prev
    Next
    INDEX
    Explanations

    phrases linking common words

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

    Ejection Fraction

    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
     बढ़ाता
    0.41
     Halt
    0.41
     Sixty
    0.40
     Mode
    0.40
     }).
    0.40
     halt
    0.40
     இற
    0.39
     itself
    0.39
    halt
    0.38
     Filled
    0.38
    POSITIVE LOGITS
     soooo
    0.44
    😩
    0.43
     오늘도
    0.42
     శ్రీ
    0.42
    你了
    0.42
    챙
    0.42
     juni
    0.41
    出版
    0.41
    平台
    0.41
    今天要
    0.41
    Activations Density 0.001%

    No Known Activations