© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 207947
    Prev
    Next
    INDEX
    Explanations

    subscription services and devices

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

    improvement and participation

    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
    Negative Logits
     अधीन
    0.51
    <unused266>
    0.46
    jaya
    0.46
    ukar
    0.45
    terior
    0.45
    embangan
    0.45
     نماز
    0.45
     permainan
    0.44
     دریافت‌شده
    0.44
    ्यास
    0.43
    POSITIVE LOGITS
    鲈
    0.48
    通讯
    0.46
    K
    0.46
     к
    0.44
     দেখো
    0.44
    L
    0.44
    Parents
    0.43
    CRM
    0.43
    联邦
    0.42
     অভিভাবকদের
    0.42
    Activations Density 0.000%

    No Known Activations