© 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. 216106
    Prev
    Next
    INDEX
    Explanations

    stock grant award

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

    focuses on outcomes and development

    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
     quantities
    0.55
    ಾ
    0.48
    are
    0.46
    連合
    0.46
    assess
    0.44
    ransport
    0.44
    ar
    0.44
    avari
    0.44
    吟
    0.43
    ry
    0.43
    POSITIVE LOGITS
     Investigación
    0.49
     decisión
    0.47
    μως
    0.45
     seh
    0.43
     Forsyth
    0.43
     méthodique
    0.43
     chaqueta
    0.42
     conosce
    0.42
     impresión
    0.41
     décret
    0.41
    Activations Density 0.000%

    No Known Activations