© 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. 19396
    Prev
    Next
    INDEX
    Explanations

    term courses

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

    open source

    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
    4
    0.84
    5
    0.82
    7
    0.81
    -
    0.74
    6
    0.73
    га
    0.70
    3
    0.70
    8
    0.68
    ۵
    0.68
    2
    0.67
    POSITIVE LOGITS
     is
    0.98
    0.83
    ↵↵
    0.58
     of
    0.56
     정
    0.56
     ของ
    0.55
    리로
    0.55
     של
    0.54
     사용
    0.54
     있다
    0.52
    Activations Density 0.383%

    No Known Activations