© 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. 177084
    Prev
    Next
    INDEX
    Explanations

    teaching them to

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

    Outputting or displaying information

    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
     bract
    0.55
    찻
    0.55
     bodice
    0.51
     beaut
    0.51
     nondestructive
    0.50
     브랜드
    0.49
     Bhuv
    0.49
     stoneware
    0.49
     obvi
    0.48
     beau
    0.47
    POSITIVE LOGITS
    END
    0.55
    پ
    0.54
    ING
    0.53
    IN
    0.53
    ep
    0.51
    ED
    0.51
    ILL
    0.50
    app
    0.50
    PER
    0.49
    s
    0.49
    Activations Density 0.000%

    No Known Activations