© 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. 143419
    Prev
    Next
    INDEX
    Explanations

    historic events and figures

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

    code block closing brace

    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
     dlatego
    0.53
     Ê
    0.51
    ěn
    0.48
    ajaran
    0.48
     ສຳ
    0.48
     kaleidos
    0.47
    isées
    0.47
    anesha
    0.46
     horizontale
    0.46
     llamadas
    0.46
    POSITIVE LOGITS
    का
    0.54
    ग
    0.53
    লা
    0.52
    गा
    0.52
    лни
    0.50
    نا
    0.50
    सा
    0.49
    Add
    0.49
    Date
    0.48
    ப
    0.48
    Activations Density 0.000%

    No Known Activations