© 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. 213182
    Prev
    Next
    INDEX
    Explanations

    foreign language plurals

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

    severe limitation

    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
    浓度
    0.47
     thermally
    0.46
    淘汰
    0.43
    沾
    0.43
    د
    0.41
    샌
    0.41
    ளை
    0.39
    焖
    0.39
    rena
    0.38
    ంగా
    0.38
    POSITIVE LOGITS
     πρώτη
    0.62
     telle
    0.55
     Lehr
    0.53
     Stunden
    0.50
     അവന്റെ
    0.50
     eerste
    0.50
     directa
    0.50
     biologie
    0.50
     la
    0.49
     zunächst
    0.49
    Activations Density 0.001%

    No Known Activations