© 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. 232624
    Prev
    Next
    INDEX
    Explanations

    systems in, Lord Vishnu, tracer wire, restraints of

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ServiceGroupID
    0.44
    Rm
    0.41
    voit
    0.40
     loosen
    0.40
     мүмк
    0.40
    .”[
    0.39
     רי
    0.39
     slay
    0.39
    
    0.39
    
    0.38
    POSITIVE LOGITS
    nosis
    0.50
    et
    0.47
    fed
    0.46
    asjon
    0.45
     Insects
    0.45
    charted
    0.44
    contracts
    0.44
    全て
    0.44
    kaz
    0.44
    học
    0.44
    Activations Density 0.000%

    No Known Activations