© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2349
    Prev
    Next
    INDEX
    Explanations

    911 and crisis Lifeline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ١
    0.33
     ១
    0.33
     ၁
    0.32
     sozialen
    0.31
     ૩
    0.30
     ServicePolicy
    0.29
     AppBsky
    0.29
    securityMarks
    0.29
    LOLL
    0.29
     QuantityOnHand
    0.29
    POSITIVE LOGITS
    .
    0.43
    ↵↵
    0.38
    ↵
    0.37
    i
    0.36
    u
    0.35
    ин
    0.33
    ′
    0.33
    の
    0.32
    re
    0.32
    ap
    0.32
    Activations Density 0.351%

    No Known Activations