© 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. 40789
    Prev
    Next
    INDEX
    Explanations

    contact with

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

    what that means

    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
     ૨
    0.52
     underlies
    0.49
    ﾀ
    0.44
     lla
    0.43
     weakens
    0.41
     disequ
    0.40
    ⊂
    0.40
    갑습니다
    0.40
     stabilizes
    0.40
    ｵ
    0.39
    POSITIVE LOGITS
     गर्व
    0.61
     więc
    0.57
     elegante
    0.56
     cadáver
    0.55
     inspirado
    0.54
     çiçek
    0.54
    เดียวกัน
    0.52
    ótico
    0.51
     mostrou
    0.50
     फर्नीचर
    0.50
    Activations Density 0.000%

    No Known Activations