© 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. 3193
    Prev
    Next
    INDEX
    Explanations

    biggest sponsorship, made by, her assigned

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

    planning financial code

    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
    ullahi
    0.50
    摸
    0.46
    튿
    0.45
    ುಕ
    0.44
    得多
    0.42
     Trabaj
    0.42
    uli
    0.41
     abges
    0.41
    ucch
    0.41
    َى
    0.41
    POSITIVE LOGITS
    beth
    0.57
     اذا
    0.55
     outflow
    0.54
    ی
    0.54
     ارب
    0.54
     برای
    0.53
     ถ้า
    0.52
     innervation
    0.52
    를
    0.51
     دانشج
    0.51
    Activations Density 0.000%

    No Known Activations