© 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. 236760
    Prev
    Next
    INDEX
    Explanations

    multilingual technical terms

    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
    รียม
    0.47
     effekt
    0.44
    CEPTION
    0.44
    িতেন
    0.43
     correspondió
    0.42
     requer
    0.41
    ب
    0.41
    TextImage
    0.41
     perfeito
    0.41
    进士
    0.40
    POSITIVE LOGITS
    ễn
    0.48
     บอก
    0.47
    膿
    0.44
    마다
    0.42
     Depuis
    0.41
     моей
    0.41
    disable
    0.41
     один
    0.40
     Caf
    0.40
    หนึ่ง
    0.40
    Activations Density 0.000%

    No Known Activations