© 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. 46231
    Prev
    Next
    INDEX
    Explanations

    capturing relevant situation

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

    Always, Fresh, never, measure

    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
    eers
    0.48
     Гинд
    0.48
     தீங்கு
    0.47
     వారికి
    0.47
    inus
    0.47
    adás
    0.47
     дз
    0.46
    }(-\
    0.46
     গবে
    0.46
    otis
    0.46
    POSITIVE LOGITS
    Very
    0.52
    අ
    0.49
    blown
    0.47
    Очень
    0.47
    [
    0.46
    நெ
    0.45
    दृश्य
    0.45
    とても
    0.45
     very
    0.44
     Lorentzian
    0.44
    Activations Density 0.000%

    No Known Activations