© 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. 103784
    Prev
    Next
    INDEX
    Explanations

    EX Series, Tensor Processing

    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
    ができる
    0.80
    자
    0.79
    смотрите
    0.77
    ре
    0.77
    ри
    0.75
    ع
    0.75
    できる
    0.73
    бо
    0.71
    ية
    0.70
    فيد
    0.69
    POSITIVE LOGITS
     brev
    0.77
    ओं
    0.76
     s
    0.75
    s
    0.72
    '!
    0.72
     Introduction
    0.71
     tweeted
    0.71
     ö
    0.70
     LEE
    0.70
     IN
    0.70
    Activations Density 0.000%

    No Known Activations