© 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-16K
    7. 11879
    Prev
    Next
    INDEX
    Explanations

    ootd photos

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

    code formatting and delimiters

    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_16k_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
     Reading
    0.51
    Reading
    0.50
    寯
    0.50
    रासत
    0.49
     decreed
    0.48
    Qin
    0.47
     ascended
    0.47
    шымта
    0.46
    ским
    0.46
     Readings
    0.46
    POSITIVE LOGITS
     할인
    0.66
     테이블
    0.65
    썸
    0.63
     타
    0.63
     평
    0.63
     댓글
    0.62
     기본
    0.61
     바
    0.61
     따라
    0.61
     영상
    0.60
    Activations Density 0.005%

    No Known Activations