© 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. 86661
    Prev
    Next
    INDEX
    Explanations

    government, data, molecule, titles

    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
    ።
    0.61
    лся
    0.59
    ৫
    0.58
     séptimo
    0.56
    ၅
    0.56
     seventh
    0.54
     ৭০
    0.54
     CtApp
    0.54
     ہوں۔
    0.54
    াপন্ন
    0.54
    POSITIVE LOGITS
    на
    0.87
    나
    0.66
    at
    0.61
    AT
    0.61
    0
    0.61
    ل
    0.59
    The
    0.57
    of
    0.55
    up
    0.52
    to
    0.52
    Activations Density 0.000%

    No Known Activations