© 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. 85432
    Prev
    Next
    INDEX
    Explanations

    protocols, endpoints, biomarkers, risk

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

    value proposition

    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
    r
    0.55
     It
    0.50
     h
    0.49
     C
    0.48
     ?",
    0.47
     Collect
    0.46
     Protect
    0.46
     Road
    0.45
     Junction
    0.45
    g
    0.45
    POSITIVE LOGITS
    渔
    0.50
     endpoints
    0.48
     biomarkers
    0.48
    饿
    0.48
    额外
    0.46
     частиц
    0.46
    险
    0.45
    额外的
    0.45
    媒
    0.45
     protocolos
    0.44
    Activations Density 0.000%

    No Known Activations