© 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. 27964
    Prev
    Next
    INDEX
    Explanations

    places and concepts

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

    code or detection

    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
     Mugh
    0.54
     Mughal
    0.49
     Ryu
    0.48
     खंड
    0.48
     Mahabhar
    0.47
     ㅅ
    0.45
     atthakath
    0.45
     Konink
    0.45
     Pampl
    0.45
     ۔۔
    0.44
    POSITIVE LOGITS
    睡
    0.42
    про
    0.41
    лья
    0.41
    ш
    0.41
    શ
    0.40
    ନ୍ଦ
    0.40
    SW
    0.39
    дру
    0.39
    эль
    0.39
    гри
    0.39
    Activations Density 0.250%

    No Known Activations