© 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. 6649
    Prev
    Next
    INDEX
    Explanations

    beginning of events or texts

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

    formal start

    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
    ดูแล
    0.39
    ियमित
    0.38
     dringend
    0.37
    สังคม
    0.37
    ท
    0.37
     linestyle
    0.36
    ચ્છ
    0.35
     Saleem
    0.35
    業務
    0.35
    羪
    0.35
    POSITIVE LOGITS
     initial
    1.03
     iniziale
    1.03
    initial
    1.00
     inicial
    0.98
     Initial
    0.95
     initiale
    0.88
    Initial
    0.87
    初始
    0.87
     শুরুতে
    0.82
     introductory
    0.82
    Activations Density 0.357%

    No Known Activations