© 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. 87310
    Prev
    Next
    INDEX
    Explanations

    music, ministries, appliance, repair

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

    direct language and factual tone

    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
    ZE
    0.48
    ery
    0.48
     B
    0.47
    ze
    0.47
    edge
    0.46
    they
    0.45
     ET
    0.45
     Zeus
    0.44
     G
    0.44
    de
    0.43
    POSITIVE LOGITS
    лли
    0.53
    强
    0.52
    зре
    0.49
    भि
    0.49
    лло
    0.49
    пенди
    0.49
    损
    0.49
    ینی
    0.48
    дям
    0.48
    хи
    0.47
    Activations Density 0.000%

    No Known Activations