© 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. 153439
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation

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

    focus on

    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
     부산
    0.49
    promote
    0.41
     ಕಬ್ಬಿಣ
    0.41
     parlour
    0.40
    부산
    0.40
    traffic
    0.40
    வ்வேறு
    0.40
    ⼀
    0.39
     চলিয়া
    0.39
     번째
    0.38
    POSITIVE LOGITS
     zuk
    0.54
    Inverse
    0.53
    Import
    0.50
     Übers
    0.49
    ോട്ട
    0.48
    Fog
    0.48
     Zert
    0.47
    ఖ్య
    0.47
     (
    0.47
    ância
    0.47
    Activations Density 0.000%

    No Known Activations