© 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. 6729
    Prev
    Next
    INDEX
    Explanations

    efficient execution

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

    lists non-English characters

    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
     Sich
    0.52
    ޗ
    0.51
     เศ
    0.50
     clarinet
    0.49
     cedo
    0.49
     CRYST
    0.48
     kristall
    0.48
     necessaria
    0.48
    ﺽ
    0.48
    ພວກເຮ
    0.47
    POSITIVE LOGITS
    et
    0.48
    随机
    0.45
    specify
    0.44
     scandals
    0.42
    马上
    0.42
    raines
    0.41
    ち
    0.41
    郁
    0.40
    olução
    0.40
    ं
    0.39
    Activations Density 0.001%

    No Known Activations