© 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. 207045
    Prev
    Next
    INDEX
    Explanations

    exotic locations, carefully, mediocre

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

    often involves describing settings

    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
    Enum
    0.61
    i
    0.48
    radio
    0.47
     enum
    0.46
    micro
    0.45
     Recorded
    0.45
    adio
    0.45
    廣
    0.45
    PathDirectory
    0.44
     Record
    0.44
    POSITIVE LOGITS
     χρησιμοποι
    0.48
    😝
    0.48
     proté
    0.48
    ＰＥＮＡＮＡ
    0.46
     Dud
    0.46
     Ciências
    0.46
     coopération
    0.45
     食器
    0.45
     hubby
    0.45
    ్‌
    0.45
    Activations Density 0.000%

    No Known Activations