© 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. 87269
    Prev
    Next
    INDEX
    Explanations

    cities including Sherbrooke

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

    parent telling, Catholic ism, demands exceptional

    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
    Not in Any Lists

    No Comments

    Negative Logits
    单纯
    0.54
     pondered
    0.45
    ம்
    0.44
    Б
    0.44
    யோ
    0.43
     одино
    0.43
    좀
    0.43
     нейтра
    0.43
    МО
    0.42
    ПО
    0.41
    POSITIVE LOGITS
    ᅦ
    0.50
    ğine
    0.48
    fortunate
    0.47
     প্রসিদ্ধ
    0.47
    োদিত
    0.47
    immune
    0.46
    chievement
    0.46
     কোথায়
    0.46
    स्ट्री
    0.46
    ofluorescence
    0.46
    Activations Density 0.001%

    No Known Activations