© 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. 98225
    Prev
    Next
    INDEX
    Explanations

    underdog, south, caramel, smooth, bag

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

    results demonstrate

    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
     ASCII
    0.56
     o
    0.56
    a
    0.52
     asterisk
    0.51
     literals
    0.50
     indicates
    0.47
     する
    0.47
     ReLU
    0.47
     using
    0.46
    у
    0.46
    POSITIVE LOGITS
    ewek
    0.49
     poils
    0.46
    然后
    0.46
    鄕
    0.45
    شون
    0.45
    ကို
    0.44
    όμε
    0.44
    锻炼
    0.44
     있고
    0.44
    شهر
    0.44
    Activations Density 0.001%

    No Known Activations