© 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. 199389
    Prev
    Next
    INDEX
    Explanations

    sworn officers or police

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

    numbers and lists

    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
     tetromino
    0.47
     opérateur
    0.43
    运算
    0.42
    来进行
    0.42
     직
    0.40
     బయ
    0.40
     scuola
    0.39
     QString
    0.39
    Acetoxy
    0.39
     liturgy
    0.39
    POSITIVE LOGITS
     також
    0.49
    繼續
    0.48
     продовжу
    0.45
    also
    0.45
    すべての
    0.42
    those
    0.42
    PGS
    0.42
     repos
    0.42
     also
    0.41
    Ī
    0.41
    Activations Density 0.002%

    No Known Activations