© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9848
    Prev
    Next
    INDEX
    Explanations

    legal processes and procedural terms

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

    exclusion zone

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

    formal professional text

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_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
     be
    0.57
    or
    0.43
     is
    0.40
     it
    0.38
    m
    0.38
    aga
    0.36
     মুক্তিবাহিনীর
    0.35
    re
    0.35
    be
    0.35
    it
    0.35
    POSITIVE LOGITS
    邡
    0.45
    맛집
    0.43
    टेज
    0.43
     Umsatz
    0.42
    运维
    0.40
    ൫
    0.40
    法语
    0.39
    низу
    0.39
    措置
    0.39
     codebase
    0.39
    Activations Density 1.489%

    No Known Activations