© 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. 94970
    Prev
    Next
    INDEX
    Explanations

    time to nap

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

    multilingual text handling

    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
    we
    0.47
    Axis
    0.46
    on
    0.44
    </em>
    0.43
    bien
    0.42
    تبر
    0.42
     ф
    0.41
    آ
    0.41
    ING
    0.41
    Sh
    0.40
    POSITIVE LOGITS
    ܘܢ
    0.54
     pierwszym
    0.50
     noires
    0.49
     เรือ
    0.49
     doit
    0.48
     devono
    0.48
    前来
    0.48
     bör
    0.47
     preschoolers
    0.47
     Örneğin
    0.47
    Activations Density 0.001%

    No Known Activations