© 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. 176504
    Prev
    Next
    INDEX
    Explanations

    The Corporation

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

    often qualifying words

    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
    ‌ای
    0.61
    ‌آ
    0.49
    ም።
    0.47
     internationalen
    0.47
     kaleidos
    0.47
    ᴊ
    0.46
    chließlich
    0.45
     américaine
    0.44
     खूबसूरती
    0.44
    openhagen
    0.44
    POSITIVE LOGITS
    ق
    0.54
    و
    0.47
     trên
    0.46
    to
    0.45
    сили
    0.45
    其他
    0.44
    結束
    0.44
    ള
    0.43
    哫
    0.43
    ጾ
    0.43
    Activations Density 0.000%

    No Known Activations