© 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. 146678
    Prev
    Next
    INDEX
    Explanations

    computational investigation of engines

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

    Insists that, recurring themes, rhythm

    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
     کراچی
    0.48
    毕业
    0.48
    谏
    0.46
    审美
    0.46
     Utama
    0.46
     Leser
    0.45
     상담
    0.45
    遐
    0.45
    मुख्यमंत्री
    0.45
    短期
    0.45
    POSITIVE LOGITS
     motors
    0.45
     membranes
    0.45
    engines
    0.45
     pipes
    0.43
    turb
    0.43
     hoses
    0.43
    eating
    0.42
     alkan
    0.42
     detergents
    0.42
     nozzles
    0.42
    Activations Density 0.000%

    No Known Activations