© 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-65K
    7. 2883
    Prev
    Next
    INDEX
    Explanations

    let me know

    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_65k_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
    <unused25>
    0.72
     મદદ
    0.67
    ConformanceMode
    0.66
     اختلافات
    0.64
     jezika
    0.64
    ilecek
    0.60
    ليم
    0.59
    -])
    0.57
    geschoss
    0.57
    $>
    0.57
    POSITIVE LOGITS
     to
    1.02
    t
    0.98
    z
    0.91
    ر
    0.82
    ,
    0.82
    ہ
    0.74
     documented
    0.73
    to
    0.72
     can
    0.70
     has
    0.70
    Activations Density 0.318%

    No Known Activations