© 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. 48742
    Prev
    Next
    INDEX
    Explanations

    dialog box

    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
    binding
    0.56
    uose
    0.54
     ორგანო
    0.51
     ناحيه
    0.51
    䡃
    0.50
    転車
    0.50
    osoma
    0.49
    祚
    0.49
     избра
    0.49
     способы
    0.48
    POSITIVE LOGITS
    ăn
    0.56
     مع
    0.54
     d
    0.50
    是
    0.49
    مة
    0.49
    ۔
    0.48
     veneers
    0.48
     avec
    0.48
    </h2>
    0.47
     build
    0.47
    Activations Density 0.008%

    No Known Activations