© 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. 261138
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    嗲
    0.48
    斧
    0.46
    發生
    0.46
     ईद
    0.45
    弭
    0.44
    Staff
    0.43
    ionali
    0.43
     उन्‍ह
    0.43
    Lisa
    0.43
    喊
    0.43
    POSITIVE LOGITS
     quantifiable
    0.47
     specified
    0.46
     identifiable
    0.46
     fluxes
    0.46
     subarrays
    0.46
     clauses
    0.45
     subclass
    0.44
     topologies
    0.44
     globules
    0.44
     simulating
    0.44
    Activations Density 0.001%

    No Known Activations