© 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. 83938
    Prev
    Next
    INDEX
    Explanations

    transaction sequence or condition

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

    alternatives or options

    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
    ς
    0.52
    数
    0.48
    目标
    0.47
    ses
    0.46
    随意
    0.46
    s
    0.46
    t
    0.46
    सी
    0.43
     цель
    0.43
    fantasy
    0.43
    POSITIVE LOGITS
     alebo
    0.55
     nebo
    0.54
     supporto
    0.54
     viac
    0.52
     contexte
    0.50
     mensajes
    0.50
     racial
    0.49
     কিংবা
    0.48
     contexto
    0.48
     precondition
    0.48
    Activations Density 0.003%

    No Known Activations