© 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. 221375
    Prev
    Next
    INDEX
    Explanations

    formal passage or document

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

    segments of

    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
    ಜ್
    0.44
     Grenze
    0.43
    ANIEL
    0.41
    ันท
    0.40
    ائِ
    0.40
    ঞ্চলিক
    0.40
    น
    0.39
     conoscenze
    0.39
    鬨
    0.39
    Stroke
    0.38
    POSITIVE LOGITS
     auster
    0.57
     ils
    0.56
     î
    0.55
    er
    0.54
    ポリシー
    0.54
    ît
    0.52
     îl
    0.52
     îm
    0.50
     policym
    0.49
     CDN
    0.49
    Activations Density 0.000%

    No Known Activations