© 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. 252495
    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
     młod
    0.48
     encephal
    0.47
     bullies
    0.47
    aden
    0.46
     kanan
    0.46
     rahu
    0.46
     प्रेम
    0.45
    බ
    0.45
     актив
    0.45
     রক্ষণ
    0.45
    POSITIVE LOGITS
    کو
    0.51
    书
    0.48
    ینے
    0.47
    zić
    0.45
     trùng
    0.45
    ضی
    0.44
    бина
    0.43
    وری
    0.43
    نی
    0.43
    以为
    0.42
    Activations Density 0.000%

    No Known Activations