© 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. 200131
    Prev
    Next
    INDEX
    Explanations

    formations and exports

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

    night light

    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
     escrever
    0.47
     म्यू
    0.47
     musician
    0.47
     indexing
    0.46
     熱
    0.46
    rição
    0.45
     viennent
    0.45
     writing
    0.45
     marinas
    0.44
     ramping
    0.44
    POSITIVE LOGITS
    exported
    0.55
    SGD
    0.50
    Bills
    0.48
    eleg
    0.48
    ählt
    0.48
    囊
    0.45
    containers
    0.45
     जंग
    0.45
     출시
    0.45
    Exports
    0.44
    Activations Density 0.000%

    No Known Activations