© 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. 164063
    Prev
    Next
    INDEX
    Explanations

    muscles produces

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

    order, problem, solution

    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
     raw
    0.46
     journeys
    0.45
    ’
    0.43
     intercepts
    0.43
     logs
    0.43
     growths
    0.42
    ین
    0.42
    يام
    0.42
     wavelengths
    0.42
    ଣ
    0.41
    POSITIVE LOGITS
    izzata
    0.48
     Metall
    0.48
     عندما
    0.47
     Gubernur
    0.47
     \,.
    0.46
     وي
    0.46
    ಂತೆ
    0.46
    фр
    0.46
     <*>
    0.45
    ɜ
    0.45
    Activations Density 0.000%

    No Known Activations