© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 143580
    Prev
    Next
    INDEX
    Explanations

    revealed findings and results

    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
    ت
    0.96
     {
    0.83
     ().
    0.75
    ب
    0.73
    т
    0.72
     дороги
    0.71
    ே
    0.70
     온
    0.69
     angiotensin
    0.69
     எ
    0.68
    POSITIVE LOGITS
    ing
    0.86
    </h3>
    0.82
    ة
    0.74
    unteers
    0.69
    さん
    0.68
    (
    0.68
    are
    0.67
     Supports
    0.66
    ance
    0.66
    l
    0.66
    Activations Density 0.003%

    No Known Activations