© 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. 119736
    Prev
    Next
    INDEX
    Explanations

    Class, member, trial, application

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

    foreign languages and specialized 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
    嶙
    0.46
     unbeatable
    0.43
    咭
    0.43
     suspiciously
    0.42
     passionately
    0.42
     transatlantic
    0.41
    दिग्ध
    0.41
     ૩
    0.40
    াবিশ
    0.40
     sélection
    0.39
    POSITIVE LOGITS
    仙
    0.47
    朝
    0.46
    內
    0.45
    父母
    0.45
    f
    0.45
     forem
    0.43
    
    0.43
    Parents
    0.43
    子供
    0.42
    芯
    0.42
    Activations Density 0.001%

    No Known Activations