© 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. 32918
    Prev
    Next
    INDEX
    Explanations

    And... a

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

    Ulaanbaatar, JSON, Disco Elysium

    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
     +
    0.52
     ()
    0.52
     Life
    0.49
     We
    0.46
     단계
    0.46
     上
    0.46
     superscript
    0.46
     |
    0.45
     var
    0.45
     四
    0.44
    POSITIVE LOGITS
     रोकता
    0.57
    áni
    0.56
    ेर
    0.54
    ат
    0.52
    ᄒ
    0.49
    ант
    0.49
    ík
    0.48
    ्न
    0.48
     inició
    0.48
     назначен
    0.48
    Activations Density 0.000%

    No Known Activations