© 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. 56726
    Prev
    Next
    INDEX
    Explanations

    needs and questions

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

    terms and conditions

    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
    could
    0.52
    ansı
    0.50
    MinIntensity
    0.50
     俺
    0.49
    imageId
    0.49
    notFound
    0.48
    WART
    0.48
     influenz
    0.48
     平均
    0.48
    UnitTest
    0.48
    POSITIVE LOGITS
     section
    0.44
     Monument
    0.43
     virtud
    0.42
    ørte
    0.42
    ᕕ
    0.42
     corollary
    0.42
     Confidential
    0.42
     Balm
    0.42
    вость
    0.41
    들이
    0.40
    Activations Density 0.000%

    No Known Activations