© 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. 95930
    Prev
    Next
    INDEX
    Explanations

    basic information

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

    complement system, familias de, Maastricht Treaty

    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
    ɲ
    0.47
    สั่ง
    0.43
    ớp
    0.42
    西班牙
    0.42
    ovaný
    0.42
     Špan
    0.42
     Spanish
    0.42
    恸
    0.42
    pImage
    0.41
    b
    0.41
    POSITIVE LOGITS
    基本的な
    0.48
     特許庁
    0.47
    引き続き
    0.47
     trouser
    0.46
    持ち
    0.45
     RADIOACTIVE
    0.44
    成り立つ
    0.44
    MARKED
    0.44
    定め
    0.44
    ITEM
    0.43
    Activations Density 0.001%

    No Known Activations