© 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. 82879
    Prev
    Next
    INDEX
    Explanations

    tires

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

    specific content or documents

    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
    ौसी
    0.53
     `<=
    0.51
     motivations
    0.48
     irradiation
    0.48
    ang
    0.47
    惊喜
    0.47
     महंगाई
    0.47
     homeschool
    0.46
     किराने
    0.46
     percussion
    0.46
    POSITIVE LOGITS
    getExtension
    0.49
    је
    0.47
    cdot
    0.46
    ческого
    0.46
    -])
    0.46
    тивна
    0.46
    ANE
    0.44
    }$-
    0.44
    ।-
    0.43
    연
    0.43
    Activations Density 0.000%

    No Known Activations