© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10875
    Prev
    Next
    INDEX
    Explanations

    variable names in code

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

    variable assignments

    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
     keine
    0.40
     hydrological
    0.40
     lazer
    0.39
     seine
    0.39
     kola
    0.39
     arrests
    0.38
    <0x1D>
    0.38
     global
    0.38
     Drey
    0.38
     eher
    0.38
    POSITIVE LOGITS
    ;
    0.47
    Avant
    0.41
    蕙
    0.40
     নেতৃত্বে
    0.40
    刖
    0.40
     =(
    0.40
    IsNot
    0.39
    ;(
    0.38
    RefItem
    0.38
    getMain
    0.38
    Activations Density 0.002%

    No Known Activations