© 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. 130362
    Prev
    Next
    INDEX
    Explanations

    will use

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

    proxy, split, oscillations, abuse, direction

    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
    Características
    0.58
    ारों
    0.48
    CRUD
    0.47
    valueOf
    0.47
    Ч
    0.47
    重庆
    0.46
    Digest
    0.46
     डेंगू
    0.45
    PHPExcel
    0.45
    ্লীল
    0.45
    POSITIVE LOGITS
     h
    0.54
     representation
    0.54
     laws
    0.54
     cline
    0.53
     r
    0.53
     population
    0.52
     mediators
    0.52
     rulemaking
    0.52
     kaufen
    0.52
     public
    0.51
    Activations Density 0.000%

    No Known Activations