© 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. 16-GEMMASCOPE-2-RES-262K
    7. 116160
    Prev
    Next
    INDEX
    Explanations

    configuration files and categories

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Ꭽ
    0.69
    영
    0.65
    נ
    0.63
    श
    0.61
    А
    0.61
    獸
    0.61
    Х
    0.60
    н
    0.59
    Khi
    0.59
    أ
    0.58
    POSITIVE LOGITS
     strategic
    0.49
    zler
    0.49
    dic
    0.48
     focal
    0.47
     metabolic
    0.47
    ons
    0.47
     diplomatic
    0.46
     migratory
    0.46
     display
    0.46
    eterminate
    0.46
    Activations Density 0.000%

    No Known Activations