© 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. 94941
    Prev
    Next
    INDEX
    Explanations

    other classifications or specifics

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

    watching videos

    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
    Timestamp
    0.43
    Breakpoint
    0.43
     VS
    0.42
    时间的
    0.42
    ;.
    0.40
     vscode
    0.40
    Appendix
    0.39
    全新的
    0.39
     descriptor
    0.38
    描述
    0.38
    POSITIVE LOGITS
     Otras
    0.55
     اخرى
    0.54
     drugi
    0.49
     exerted
    0.47
    ക്കൂ
    0.47
    <unused244>
    0.46
     weekly
    0.46
     ಕೇಂದ್ರ
    0.46
     Telef
    0.46
    alq
    0.46
    Activations Density 0.001%

    No Known Activations