© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 249579
    Prev
    Next
    INDEX
    Explanations

    non-english words

    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
    纳入
    0.45
    /
    0.45
    ⊙
    0.44
    ading
    0.44
     hearings
    0.43
    問い合わせ
    0.41
    WAY
    0.41
    垒
    0.41
    ウェイ
    0.41
     rulings
    0.40
    POSITIVE LOGITS
     তোমাকে
    0.56
     போய்
    0.54
     Thương
    0.51
     Και
    0.50
     তুমি
    0.49
     Nirm
    0.48
    你在
    0.48
     restos
    0.47
     Happiness
    0.47
     Haram
    0.46
    Activations Density 0.000%

    No Known Activations