© 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. 141441
    Prev
    Next
    INDEX
    Explanations

    descriptive clauses

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

    learn by watching

    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
    Scopes
    0.52
     chacun
    0.47
    o
    0.46
     atenção
    0.44
     quisquam
    0.44
     upang
    0.42
     Sudan
    0.40
    quare
    0.39
     Ying
    0.39
     oamen
    0.39
    POSITIVE LOGITS
     Normdatei
    0.54
    cyj
    0.52
     バー
    0.49
    σή
    0.47
    addDigit
    0.46
     即
    0.46
    蔻
    0.45
    τζ
    0.44
     పొ
    0.43
     ას
    0.43
    Activations Density 0.000%

    No Known Activations