© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 257562
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    0.50
    w
    0.49
     وس
    0.47
     روش
    0.47
    of
    0.46
    </strong>
    0.46
    dual
    0.45
    n
    0.45
     وات
    0.44
     Siddh
    0.43
    POSITIVE LOGITS
     noqa
    0.50
    াত্মক
    0.49
    ディレクトリ
    0.48
    รัก
    0.47
     Directeur
    0.47
     இயக்கு
    0.47
     attenzione
    0.46
     atenção
    0.46
     প্রতিরক্ষা
    0.45
    梦
    0.44
    Activations Density 0.001%

    No Known Activations