© 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. 135923
    Prev
    Next
    INDEX
    Explanations

    any person or vessel

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

    strategic decisions, Fiber Optic

    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
     嗯
    0.57
    lcii
    0.53
     diesen
    0.51
     മുൻ
    0.51
     ergeben
    0.50
     trialComponents
    0.49
     espíritu
    0.48
    AppBsky
    0.48
     ನಡೆಸ
    0.48
     感じ
    0.47
    POSITIVE LOGITS
     to
    0.67
     pathological
    0.53
     a
    0.52
     that
    0.52
     inflammatory
    0.49
     pause
    0.45
     Care
    0.45
    نه
    0.45
     one
    0.45
     popsicle
    0.45
    Activations Density 0.001%

    No Known Activations