© 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. 77296
    Prev
    Next
    INDEX
    Explanations

    international operations and activities

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

    personal stories, cultures, values

    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
     جديدة
    0.54
    新しい
    0.49
    畨
    0.49
    とする
    0.49
     새로운
    0.49
    の新
    0.47
    ใหม่
    0.45
    㐌
    0.45
     പുതിയ
    0.44
     RANDOM
    0.44
    POSITIVE LOGITS
     আবেদ
    0.47
     internasional
    0.45
     operasi
    0.45
     ogrom
    0.44
     operadores
    0.44
     estab
    0.43
     operation
    0.42
     mengirim
    0.42
     salaries
    0.42
     karyawan
    0.42
    Activations Density 0.010%

    No Known Activations