© 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. 16769
    Prev
    Next
    INDEX
    Explanations

    NeurIPS and Pitts

    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
    <0x0D>
    0.93
    ick
    0.79
    unts
    0.75
    رل
    0.71
    r
    0.71
    unus
    0.69
     sported
    0.69
    2
    0.69
    وض
    0.68
    0.68
    POSITIVE LOGITS
    ן
    1.16
     as
    0.95
    ၁
    0.89
    ο
    0.85
    ١
    0.76
    ری
    0.74
     voyage
    0.73
     geliştir
    0.73
    人
    0.72
    ૧
    0.72
    Activations Density 0.000%

    No Known Activations