© 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. 209290
    Prev
    Next
    INDEX
    Explanations

    limit of the City

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

    foreign language markers

    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
    a
    0.67
    i
    0.59
    an
    0.57
    citizens
    0.52
    getAbsolutePath
    0.48
    frak
    0.48
    scalable
    0.48
    testing
    0.46
    rq
    0.46
    u
    0.46
    POSITIVE LOGITS
    я
    0.57
    ід
    0.56
    вер
    0.49
     préférence
    0.47
     startIndex
    0.46
    ्वे
    0.46
     că
    0.46
     них
    0.45
    нора
    0.45
    лот
    0.45
    Activations Density 0.000%

    No Known Activations