© 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. 216309
    Prev
    Next
    INDEX
    Explanations

    features normally

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

    breakdown, increment, CW, nuances, intersect

    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
    Not in Any Lists

    No Comments

    Negative Logits
     rhin
    0.50
     patties
    0.48
     esophagus
    0.46
     appropriations
    0.45
     inoculation
    0.45
    ₚ
    0.44
     fluctuations
    0.44
    諷
    0.44
     installations
    0.44
     conservatives
    0.44
    POSITIVE LOGITS
    ü
    0.53
    ة
    0.46
    ﹝
    0.45
     Avalon
    0.45
    recorded
    0.45
    }=-
    0.45
    გ
    0.44
     Unified
    0.44
    (',
    0.44
     ബ്രി
    0.43
    Activations Density 0.000%

    No Known Activations