© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2559
    Prev
    Next
    INDEX
    Explanations

    python code using numpy

    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_65k_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
     JG
    1.13
     Fant
    1.11
     OPS
    1.11
     MANAGER
    1.08
     HISTORY
    1.07
    ﯽ
    1.07
     ジ
    1.06
    歴史
    1.05
     ټول
    1.05
     Jungkook
    1.03
    POSITIVE LOGITS
    坐标
    0.94
    memset
    0.91
     regenv
    0.88
     graphic
    0.88
    setString
    0.87
     determining
    0.86
     directions
    0.86
    umbers
    0.84
     अग्र
    0.84
     advising
    0.83
    Activations Density 0.005%

    No Known Activations