© 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. 17092
    Prev
    Next
    INDEX
    Explanations

    poker society

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

    amounts and ratios

    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
     is
    0.50
    ome
    0.45
     Continued
    0.44
    wand
    0.43
     D
    0.42
    ell
    0.42
     DC
    0.41
    hang
    0.41
    ali
    0.40
    null
    0.40
    POSITIVE LOGITS
    нтэр
    0.54
     apoio
    0.47
    ﻨ
    0.46
    কৃ
    0.45
    λέον
    0.45
    人了
    0.45
     Förderung
    0.45
    িত্য
    0.44
    جاج
    0.44
    ерт
    0.43
    Activations Density 0.000%

    No Known Activations