© 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. 80014
    Prev
    Next
    INDEX
    Explanations

    elements listed for items

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    0.46
     enable
    0.43
    陪
    0.42
     help
    0.41
    ENABLE
    0.40
    فيد
    0.40
     {
    0.39
     jur
    0.39
     nurture
    0.39
     {},
    0.38
    POSITIVE LOGITS
    
    0.54
    టీఎం
    0.53
     सुपारी
    0.51
     pú
    0.50
    isex
    0.50
     toothbrush
    0.48
     barbaric
    0.46
    Toilet
    0.46
     रिप्रोड
    0.46
     समुद्रा
    0.46
    Activations Density 0.003%

    No Known Activations