© 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. 250936
    Prev
    Next
    INDEX
    Explanations

    name is

    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
     гульнявыя
    0.48
     Exchequer
    0.47
     χρη
    0.45
     ଆ
    0.45
     cài
    0.43
     ರೋ
    0.42
     ተመሳሳይ
    0.42
     zapewn
    0.42
     পরিষে
    0.42
    живання
    0.41
    POSITIVE LOGITS
     from
    0.53
    2
    0.52
     but
    0.50
    3
    0.48
    but
    0.46
    4
    0.45
     ortho
    0.45
    it
    0.45
     in
    0.43
     beyond
    0.43
    Activations Density 0.003%

    No Known Activations