© 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. 117275
    Prev
    Next
    INDEX
    Explanations

    braid, Dutch braid

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

    specific branching

    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
     সেইরূপ
    0.53
     처
    0.49
     Р
    0.47
     말씀
    0.46
     Дон
    0.46
     부동산
    0.46
     버
    0.45
    erade
    0.45
     казіно
    0.45
     проблеми
    0.45
    POSITIVE LOGITS
    ريم
    0.45
    produto
    0.44
    دخل
    0.44
    站
    0.43
    之前
    0.43
     entrou
    0.43
    logo
    0.42
    بل
    0.41
    impress
    0.41
    陌
    0.40
    Activations Density 0.001%

    No Known Activations