© 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. 39820
    Prev
    Next
    INDEX
    Explanations

    averaging and division

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

    average calculation

    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
    现场
    0.41
     verzi
    0.40
     версии
    0.39
     Connie
    0.39
     लाह
    0.38
    setScene
    0.37
    ẏ
    0.37
     Ange
    0.36
    iseaux
    0.36
    椰
    0.36
    POSITIVE LOGITS
     averaged
    0.64
     averaging
    0.62
     averages
    0.57
    Average
    0.55
    averaged
    0.54
     Aver
    0.53
    AVER
    0.53
     AVER
    0.52
     Average
    0.51
     divided
    0.51
    Activations Density 0.009%

    No Known Activations