© 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. 39597
    Prev
    Next
    INDEX
    Explanations

    AP Top

    np_acts-logits-general · gemini-2.5-flash-lite

    political affiliation; sumō rank; technical requests

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     മുതല്‍
    0.48
     etiquetas
    0.47
     Š
    0.47
     बढ़ावा
    0.47
     または
    0.46
     already
    0.46
     outperforms
    0.44
     previamente
    0.43
     permitirá
    0.43
     ຫຼື
    0.43
    POSITIVE LOGITS
    玾
    0.50
    ViewController
    0.49
    bar
    0.43
     प्रतियोग
    0.41
    ointe
    0.41
    ре
    0.40
    ^-
    0.40
    悟
    0.39
    ဏ
    0.39
     bizony
    0.39
    Activations Density 0.000%

    No Known Activations