© 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. 180194
    Prev
    Next
    INDEX
    Explanations

    nationwide cases or recently treated

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

    consistent, variable, quickly dynamic

    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
     впечат
    0.55
     مفه
    0.54
     호출
    0.54
     रेट
    0.53
     अमेरिकी
    0.52
     అమె
    0.52
     अमेर
    0.50
    setminus
    0.50
     ਟ
    0.49
    ເຮັດ
    0.48
    POSITIVE LOGITS
    ك
    0.50
    1
    0.49
     /
    0.49
     ac
    0.48
     (
    0.48
     vidare
    0.48
    a
    0.47
    ان
    0.46
     to
    0.46
     sexu
    0.46
    Activations Density 0.001%

    No Known Activations