© 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. 76078
    Prev
    Next
    INDEX
    Explanations

    week today of the week

    np_acts-logits-general · gemini-2.5-flash-lite

    times and unfortunate circumstances

    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
    ен
    0.41
    ыз
    0.40
    শালী
    0.40
    shiny
    0.40
     polluted
    0.39
    вающий
    0.38
    ويه
    0.38
     defamatory
    0.38
    но
    0.38
    蛰
    0.37
    POSITIVE LOGITS
     receipts
    0.55
     attempts
    0.46
     feit
    0.46
     shutdowns
    0.45
     이날
    0.45
     orphans
    0.45
     openers
    0.45
     hours
    0.45
     bills
    0.45
     kickoff
    0.45
    Activations Density 0.002%

    No Known Activations