© 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. 51673
    Prev
    Next
    INDEX
    Explanations

    first action

    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
     их
    0.42
    <s>
    0.38
    their
    0.38
     Writers
    0.38
    厡
    0.37
     Their
    0.37
     उनकी
    0.35
     sited
    0.34
    ted
    0.34
     $,
    0.34
    POSITIVE LOGITS
     você
    0.55
     możesz
    0.54
    ！
    0.50
     vaše
    0.48
     당신
    0.48
     tienes
    0.48
    ර්
    0.47
     iyong
    0.46
     morate
    0.46
     あなた
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.