© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9673
    Prev
    Next
    INDEX
    Explanations

    dataframe assignment

    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
     Gears
    0.87
    屐
    0.86
    rods
    0.86
    horns
    0.86
    手中的
    0.85
     الدفاع
    0.85
    Foreign
    0.84
     внешней
    0.84
    棍
    0.82
    ears
    0.81
    POSITIVE LOGITS
     igualdad
    0.99
     ali
    0.97
    ¹,
    0.97
     szület
    0.97
     espont
    0.96
     baseURL
    0.95
     distrib
    0.94
    ਔ
    0.94
     forever
    0.94
     saldo
    0.93
    Activations Density 0.005%

    No Known Activations