© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 31655
    Prev
    Next
    INDEX
    Explanations

    CT1~CT8

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

    私は学生

    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
     Бүгенге
    0.45
    饴
    0.45
    မှုကို
    0.45
    ังสือ
    0.43
    affaires
    0.43
    ленность
    0.42
    ടുത
    0.42
     Seafood
    0.42
     Yeast
    0.41
     Newmarket
    0.41
    POSITIVE LOGITS
     [\
    0.47
     parametrized
    0.47
     euclidean
    0.46
     convoluted
    0.46
     latex
    0.45
     cringe
    0.44
     \,\
    0.44
     denoted
    0.44
    -\
    0.43
     \
    0.43
    Activations Density 0.007%

    No Known Activations