© 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. 84464
    Prev
    Next
    INDEX
    Explanations

    two languages

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

    numbers and specific terms

    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
    ＇
    0.48
    綻
    0.48
    䇝
    0.48
    ボディ
    0.46
     പ്രതിഷേധ
    0.46
    葲
    0.44
     கொ
    0.44
    秒
    0.44
     ಅರ್
    0.43
    ﹋
    0.43
    POSITIVE LOGITS
     indexes
    0.52
     prefixes
    0.52
     two
    0.51
     zwei
    0.51
     indexOf
    0.48
     clara
    0.47
     dwóch
    0.47
     additional
    0.46
     acute
    0.46
     deux
    0.46
    Activations Density 0.000%

    No Known Activations