© 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. 191088
    Prev
    Next
    INDEX
    Explanations

    requests for new assignments

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

    sprocket analysis expertise

    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
    ឈ
    0.50
    tiger
    0.47
    torque
    0.46
    szer
    0.45
     rod
    0.44
    tube
    0.43
     atrophy
    0.43
     habitaciones
    0.42
     알
    0.42
     suction
    0.42
    POSITIVE LOGITS
    лин
    0.48
     छंद
    0.47
     Maurer
    0.47
    主办
    0.47
     Hackett
    0.46
    訢
    0.46
    espace
    0.45
     लैंग
    0.44
    лін
    0.43
     کوتاه
    0.42
    Activations Density 0.001%

    No Known Activations