© 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. 91638
    Prev
    Next
    INDEX
    Explanations

    specific medical phrases

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

    new / foreign words

    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
     হাদী
    0.50
    addock
    0.48
    steigen
    0.48
    迳
    0.46
    ashed
    0.46
    딪
    0.46
     uključ
    0.45
    ربية
    0.45
     korišten
    0.45
    ח
    0.45
    POSITIVE LOGITS
    Consumers
    0.44
     yeasts
    0.44
     volcanoes
    0.44
     consumers
    0.43
     microorganisms
    0.43
     deities
    0.43
     excavations
    0.43
     complexes
    0.42
     crows
    0.42
    Nature
    0.42
    Activations Density 0.001%

    No Known Activations