© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10018
    Prev
    Next
    INDEX
    Explanations

    float, floating things, Floyd

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

    floating point

    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_40_width_16k_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
    omt
    0.47
    掛
    0.43
     Skipping
    0.40
    ici
    0.38
    alur
    0.38
    ergy
    0.38
    }-\
    0.38
    歡迎
    0.37
    burner
    0.37
    $.\
    0.37
    POSITIVE LOGITS
    浮か
    0.80
    浮
    0.75
     Flo
    0.73
     Floating
    0.71
    parseFloat
    0.70
     floated
    0.69
    Floating
    0.67
     float
    0.66
     FLO
    0.66
     FLOAT
    0.66
    Activations Density 0.054%

    No Known Activations