© 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. 92516
    Prev
    Next
    INDEX
    Explanations

    companies directory

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

    then check

    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
    ਮ
    0.54
    を図
    0.52
    ব্ব
    0.52
    ilerinin
    0.51
    Mama
    0.48
    बर्ट
    0.47
    やま
    0.46
    ब्बा
    0.46
     formalism
    0.46
     posthum
    0.46
    POSITIVE LOGITS
     unbear
    0.46
    phus
    0.46
    nali
    0.45
    록
    0.44
     عنده
    0.43
    ciąż
    0.42
     الده
    0.42
    record
    0.41
    ชนะ
    0.41
    ridges
    0.40
    Activations Density 0.001%

    No Known Activations