© 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. 204117
    Prev
    Next
    INDEX
    Explanations

    cross floodwaters

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

    code assignments and variable sizing

    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
     scanty
    0.48
    า
    0.44
     Texts
    0.43
    ଠ
    0.43
     nymphs
    0.42
    ن
    0.42
    IN
    0.42
    ructures
    0.41
     syll
    0.41
     miel
    0.41
    POSITIVE LOGITS
    ﷻ
    0.54
    bean
    0.52
    حب
    0.52
    чение
    0.51
    hasClass
    0.49
    BuildContext
    0.47
    機
    0.47
    人員
    0.46
     የመጀመሪያ
    0.46
    第一個
    0.46
    Activations Density 0.000%

    No Known Activations