© 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. 36783
    Prev
    Next
    INDEX
    Explanations

    staff

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

    defining scope and attributes

    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
     נו
    0.52
     よ
    0.50
     いっ
    0.46
     ז
    0.46
     感じ
    0.46
    achtet
    0.45
     جي
    0.45
     ء
    0.45
     ২০১৪
    0.44
     なさい
    0.44
    POSITIVE LOGITS
     permettant
    0.51
     allong
    0.43
     Arboretum
    0.42
     Decorative
    0.42
     dekor
    0.42
     Scope
    0.41
    𝕖
    0.41
     lys
    0.41
    بین
    0.40
     espèces
    0.40
    Activations Density 0.000%

    No Known Activations