© 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. 207081
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific terms

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

    risk, weakness, purpose

    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
    öffnung
    0.52
    чний
    0.47
     চ্যাম্প
    0.46
    zych
    0.45
    endan
    0.45
    sprogram
    0.45
    ových
    0.44
    icky
    0.44
    Ọ
    0.44
    olls
    0.43
    POSITIVE LOGITS
     حاجات
    0.54
    剡
    0.53
     medio
    0.52
     amplia
    0.51
     erud
    0.51
     szer
    0.49
     gente
    0.48
     continuo
    0.48
     và
    0.47
    ../../
    0.47
    Activations Density 0.000%

    No Known Activations