© 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. 195798
    Prev
    Next
    INDEX
    Explanations

    game or activity

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

    leading teams

    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
    ｐ
    0.46
    ंपल
    0.46
    ｇ
    0.45
    াড়ি
    0.44
    keywords
    0.43
    ยนต์
    0.43
    ਰੇ
    0.42
     endpoints
    0.42
    বধূ
    0.41
    ンプ
    0.41
    POSITIVE LOGITS
     ပြော
    0.52
     délic
    0.51
     lask
    0.51
     vieille
    0.50
     ≈
    0.50
    最新的
    0.49
     ز
    0.49
     klass
    0.49
     może
    0.48
     பழைய
    0.48
    Activations Density 0.000%

    No Known Activations