© 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. 20864
    Prev
    Next
    INDEX
    Explanations

    directly

    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
    Y
    0.66
    {
    0.62
    HEIGHT
    0.60
    日に
    0.55
    Ⓘ
    0.51
     rozwią
    0.50
    もら
    0.50
    ų
    0.50
     jednostavno
    0.50
    ittää
    0.49
    POSITIVE LOGITS
    s
    0.90
    ت
    0.86
    ات
    0.76
    t
    0.75
    к
    0.74
     from
    0.74
    ों
    0.73
    ل
    0.72
     with
    0.72
    es
    0.69
    Activations Density 0.011%

    No Known Activations