© 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. 207021
    Prev
    Next
    INDEX
    Explanations

    language or technical terms

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

    numbers and bit precision

    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
    Not in Any Lists

    No Comments

    Negative Logits
    আমার
    0.58
     আমার
    0.55
    Yes
    0.50
    사의
    0.47
    =
    0.46
    商業
    0.45
    ನಿ
    0.45
    ני
    0.45
    我が
    0.45
    ________
    0.44
    POSITIVE LOGITS
     lign
    0.48
     Dokument
    0.47
     DRAM
    0.47
    dokument
    0.45
     komplet
    0.44
    ียบ
    0.43
     multilingual
    0.43
     dokument
    0.42
     MEM
    0.41
     도형
    0.41
    Activations Density 0.000%

    No Known Activations