© 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. 132387
    Prev
    Next
    INDEX
    Explanations

    solutions, offers, actions

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

    sports betting

    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
    ’
    0.51
     Developments
    0.45
    ographic
    0.44
     our
    0.43
     Very
    0.43
     Asiatic
    0.42
     and
    0.42
     certain
    0.42
     Lipid
    0.41
     (
    0.41
    POSITIVE LOGITS
     решение
    0.61
     megold
    0.56
     çözüm
    0.54
     покуп
    0.52
     راجس
    0.51
    ✞
    0.50
     рішення
    0.50
     ofert
    0.48
    签约
    0.48
     પ્રય
    0.48
    Activations Density 0.001%

    No Known Activations