© 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. 235576
    Prev
    Next
    INDEX
    Explanations

    analyzing or comparing actions

    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
    Negative Logits
     vaccinations
    0.48
    ಹಾಸ
    0.48
     mappings
    0.47
    鳖
    0.47
     syllables
    0.46
     disturbances
    0.46
     handbags
    0.46
     depots
    0.46
     bass
    0.46
     polyurethane
    0.46
    POSITIVE LOGITS
     Анали
    0.50
    Legend
    0.46
    Against
    0.45
    м
    0.45
    analyze
    0.44
     Син
    0.44
    createUser
    0.43
    Customize
    0.43
    real
    0.43
    Comparing
    0.43
    Activations Density 0.001%

    No Known Activations