© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 28027
    Prev
    Next
    INDEX
    Explanations

    chapter involvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
     causado
    0.58
     процессы
    0.50
    棻
    0.50
     व्यक्ति
    0.50
     motivos
    0.49
     plástico
    0.49
     થી
    0.49
    嬌
    0.48
     മനുഷ്യ
    0.47
     содержание
    0.47
    POSITIVE LOGITS
    T
    0.69
    on
    0.68
    s
    0.62
    act
    0.59
    st
    0.59
    L
    0.57
    l
    0.55
    j
    0.55
    S
    0.54
    ad
    0.54
    Activations Density 0.000%

    No Known Activations