© 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. 16-GEMMASCOPE-2-RES-262K
    7. 107340
    Prev
    Next
    INDEX
    Explanations

    HTTP Provider, Principal Protection

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     barns
    0.55
    lname
    0.52
    barn
    0.50
    罰
    0.49
     financed
    0.48
     divisions
    0.48
     enemies
    0.47
     specialties
    0.47
     markers
    0.47
     finance
    0.46
    POSITIVE LOGITS
    Recommended
    0.56
    Unexpected
    0.52
    ۰
    0.52
    Hik
    0.50
    Crist
    0.49
    兎
    0.48
     Lettuce
    0.47
    Rounding
    0.46
    Luxury
    0.46
    Veronica
    0.45
    Activations Density 0.000%

    No Known Activations