© 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. 122211
    Prev
    Next
    INDEX
    Explanations

    financial or descriptive terms

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

    CORS and web development

    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
     fundament
    0.47
    )&=
    0.46
     loc
    0.43
     syst
    0.43
    uição
    0.42
    ının
    0.41
     sumber
    0.41
    =========
    0.41
     ular
    0.41
     daly
    0.41
    POSITIVE LOGITS
    好
    0.65
    喜欢
    0.55
    ভালোবাস
    0.54
     ভালোবাস
    0.53
     ভালোবাসা
    0.53
    可愛
    0.52
    闶
    0.52
    喜歡
    0.52
    节日
    0.50
    小
    0.49
    Activations Density 0.003%

    No Known Activations