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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3170
    Prev
    Next
    INDEX
    Explanations

    is part of or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    is
    0.70
     are
    0.64
    a
    0.63
     which
    0.62
    i
    0.62
    which
    0.61
    ०
    0.54
    ت
    0.54
    Are
    0.53
    いる
    0.52
    POSITIVE LOGITS
    ͤ
    0.68
     아닙
    0.65
     아니다
    0.65
     лишь
    0.65
    currentUser
    0.64
     توسط
    0.64
    ysseus
    0.64
     Перейти
    0.63
     而且
    0.63
     아니
    0.63
    Activations Density 0.271%

    No Known Activations