© 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. 103633
    Prev
    Next
    INDEX
    Explanations

    singular values, trace

    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
     mercados
    0.66
     शहरा
    0.62
     डिफ
    0.60
     volcanoes
    0.60
    $),
    0.59
    льники
    0.58
    щих
    0.58
    ޮ
    0.57
     inventories
    0.57
     intrusions
    0.57
    POSITIVE LOGITS
    per
    0.66
     prend
    0.61
     中
    0.55
    の後
    0.54
    time
    0.54
    un
    0.53
    up
    0.52
    原
    0.50
     ก่อน
    0.50
    đen
    0.50
    Activations Density 0.000%

    No Known Activations