© 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. 9455
    Prev
    Next
    INDEX
    Explanations

    patients, billion, expenses, voters

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

    list structure and formatting

    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
    ा
    0.50
    ेंट
    0.46
    ers
    0.46
    8
    0.45
    a
    0.45
    丽
    0.44
    ी
    0.43
    ей
    0.42
    à
    0.42
    état
    0.41
    POSITIVE LOGITS
     withdrawing
    0.51
     withdrawn
    0.50
     excreted
    0.48
     hereinafter
    0.47
     keď
    0.46
     withdrew
    0.46
     ambayo
    0.46
     সর্বপ্রথম
    0.46
     الذين
    0.45
     অবশিষ্ট
    0.45
    Activations Density 0.000%

    No Known Activations