© 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-16K
    7. 11586
    Prev
    Next
    INDEX
    Explanations

    industry reports

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

    rejects

    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_16k_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
     政
    0.46
     Amended
    0.44
     处理
    0.44
     रेसिपी
    0.44
     Travelers
    0.43
     Coupled
    0.41
     Bismillahirrah
    0.41
     开发
    0.40
    响
    0.40
    IDAY
    0.40
    POSITIVE LOGITS
    alade
    0.47
    ancourt
    0.45
     conquest
    0.44
    argument
    0.43
    ে
    0.43
     cortex
    0.42
     bronch
    0.42
    converter
    0.42
     Khr
    0.42
    ভারতে
    0.42
    Activations Density 0.002%

    No Known Activations