© 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. 159882
    Prev
    Next
    INDEX
    Explanations

    accusations and transfers

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

    Quote

    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
     آزم
    0.45
     actuación
    0.44
    ндә
    0.43
     теркәлү
    0.41
    观测
    0.40
    .}\
    0.39
     equação
    0.39
     terang
    0.39
     testicule
    0.39
     सूत्रकृमि
    0.38
    POSITIVE LOGITS
    向
    0.44
     মিছিল
    0.44
    ব্যবহার
    0.43
    uem
    0.42
     ベージュ
    0.42
    t
    0.42
     একটু
    0.42
    らしい
    0.41
     こちら
    0.41
    রব
    0.41
    Activations Density 0.004%

    No Known Activations