© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 35500
    Prev
    Next
    INDEX
    Explanations

    recording data 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
    س
    1.13
     records
    0.96
    с
    0.96
    ’
    0.96
    s
    0.94
    records
    0.92
    Т
    0.92
     Record
    0.88
    embalikan
    0.88
    و
    0.88
    POSITIVE LOGITS
    is
    1.02
    _
    0.99
    ต์
    0.95
    お客様
    0.93
    لي
    0.87
    দের
    0.85
     nécessaire
    0.82
     legitim
    0.80
     bằng
    0.78
    Recorded
    0.77
    Activations Density 0.002%

    No Known Activations