© 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. 209701
    Prev
    Next
    INDEX
    Explanations

    pronouns and comparisons

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

    medical context and specific examples

    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
    鬱
    0.52
    笔记本
    0.50
     manqu
    0.48
    妝
    0.47
    পাঠ
    0.46
    ాత
    0.45
    ার্চ
    0.44
    בודה
    0.43
    细节
    0.43
    新鲜
    0.43
    POSITIVE LOGITS
     Tun
    0.49
     Ala
    0.48
    ènement
    0.48
     Clinical
    0.47
    tun
    0.47
     \
    0.46
    }{
    0.46
    b
    0.46
     American
    0.45
     ('
    0.45
    Activations Density 0.000%

    No Known Activations