© 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. 250438
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
    本来
    0.48
    लाब
    0.48
    ៨
    0.46
    води
    0.46
     व्ही
    0.44
    дно
    0.44
     विकिरण
    0.43
    映像
    0.42
    8
    0.42
    빙
    0.42
    POSITIVE LOGITS
     pomocą
    0.50
     determinación
    0.50
     różnych
    0.48
     ragion
    0.48
     limpio
    0.47
     проводят
    0.47
     späteren
    0.47
    itton
    0.47
    una
    0.46
     pasir
    0.46
    Activations Density 0.000%

    No Known Activations