© 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. 149923
    Prev
    Next
    INDEX
    Explanations

    fully integrated

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

    clarification, details, and specific terms

    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
    GISLATIVE
    0.48
    iant
    0.46
     उजा
    0.46
    FORMATION
    0.45
    imageData
    0.45
     τό
    0.44
    ផ្ត
    0.44
    r
    0.44
     torment
    0.44
    rectangular
    0.43
    POSITIVE LOGITS
     ആരോഗ്യ
    0.44
    Justice
    0.44
    감이
    0.44
    য়েড
    0.43
    Health
    0.42
    劲
    0.42
    شتی
    0.41
    ֮
    0.41
    Yes
    0.41
    वेळी
    0.41
    Activations Density 0.001%

    No Known Activations