© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80876
    Prev
    Next
    INDEX
    Explanations

    passion and violations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    of
    0.51
    é
    0.50
    for
    0.49
    three
    0.48
    ration
    0.48
    tr
    0.48
    five
    0.48
    ảng
    0.47
    friction
    0.46
    am
    0.46
    POSITIVE LOGITS
     revise
    0.47
    ᗜ
    0.46
     lowers
    0.45
     noss
    0.44
     nadie
    0.44
    𒉿
    0.43
    ўні
    0.43
     dust
    0.41
     respiratoires
    0.41
    ጕ
    0.41
    Activations Density 0.003%

    No Known Activations