© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 16218
    Prev
    Next
    INDEX
    Explanations

    function calls with arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    에서
    0.91
     ab
    0.91
     merge
    0.79
     united
    0.79
     manage
    0.79
    의
    0.78
     random
    0.76
        
    0.75
    장
    0.73
    에서의
    0.72
    POSITIVE LOGITS
    Pyrimidine
    1.28
     Juillet
    1.22
    culas
    1.21
    സിന്
    1.17
    $">
    1.17
    setStyleSheet
    1.16
     Dorey
    1.15
     библиоте
    1.15
    ilberger
    1.15
     Beaucoup
    1.13
    Activations Density 0.003%

    No Known Activations