© 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. 4902
    Prev
    Next
    INDEX
    Explanations

    identifiers with following separators

    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
    C
    0.60
     إدارة
    0.55
    V
    0.54
    Type
    0.53
    H
    0.53
    IZE
    0.52
    Password
    0.51
    er
    0.48
    Handle
    0.48
    Keyboard
    0.48
    POSITIVE LOGITS
     smokers
    0.50
     przeci
    0.50
     wsp
    0.48
     sprinter
    0.47
     porówn
    0.47
     Chiron
    0.46
    ೮
    0.46
     smoker
    0.46
    ocles
    0.46
     fron
    0.45
    Activations Density 0.006%

    No Known Activations