© 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. 75506
    Prev
    Next
    INDEX
    Explanations

    available and add

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

    Calculate Directional Movement

    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
    verick
    0.51
    ini
    0.51
    thirty
    0.51
     도
    0.50
     Esse
    0.49
    gak
    0.49
     अबा
    0.48
    oniazid
    0.48
    oa
    0.46
    Ton
    0.46
    POSITIVE LOGITS
    しまう
    0.48
    運行
    0.46
    مت
    0.45
    備
    0.45
    我們的
    0.44
    ของเรา
    0.44
    قتها
    0.44
    Наша
    0.44
    ط
    0.43
    環境
    0.43
    Activations Density 0.000%

    No Known Activations