© 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. 69316
    Prev
    Next
    INDEX
    Explanations

    listing for, group rates

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

    .py / .ipynb file

    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
     apresentado
    0.46
    施工
    0.42
    scroll
    0.42
     denominated
    0.41
    rest
    0.40
     upregulated
    0.39
    来源
    0.39
    康
    0.39
    mäss
    0.39
     genoemd
    0.38
    POSITIVE LOGITS
    รร
    0.53
     догово
    0.52
     общего
    0.49
    utations
    0.48
     побе
    0.48
    ირი
    0.48
     भगवान
    0.47
     बला
    0.47
     affidavits
    0.45
     எச்ச
    0.45
    Activations Density 0.000%

    No Known Activations