© 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. 180242
    Prev
    Next
    INDEX
    Explanations

    roles and activities

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

    safety and reliability information

    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
     за
    0.46
    绕
    0.45
    制的
    0.45
    ခြ
    0.44
     વાંચ
    0.44
     પોતા
    0.43
    ことにより
    0.43
     battle
    0.42
     Мария
    0.42
     оценка
    0.42
    POSITIVE LOGITS
     outlets
    0.52
    ک
    0.52
    Outlet
    0.50
     Shed
    0.49
    صاب
    0.47
     Outlet
    0.45
    Canc
    0.45
    canc
    0.45
     UpdateWindow
    0.45
    ن
    0.44
    Activations Density 0.000%

    No Known Activations