© 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. 1857
    Prev
    Next
    INDEX
    Explanations

    pyspark Spark

    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
    -/
    0.54
    cons
    0.47
    led
    0.47
    tered
    0.46
    tar
    0.44
    cass
    0.44
    ಂಟ
    0.43
     tray
    0.41
    pc
    0.41
    “-
    0.41
    POSITIVE LOGITS
     необы
    0.93
     ابن
    0.86
     عطا
    0.85
    Johann
    0.83
     klasik
    0.81
     thơm
    0.80
    WebpackPlugin
    0.80
     sostiene
    0.80
     querida
    0.80
    <unused473>
    0.79
    Activations Density 0.037%

    No Known Activations