© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10882
    Prev
    Next
    INDEX
    Explanations

    file names and extensions

    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_22_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
     cheg
    0.94
     تقدم
    0.90
     Green
    0.87
    กิจ
    0.86
    绿
    0.86
    หน้า
    0.85
     冬
    0.85
    内地
    0.84
     Com
    0.84
     Come
    0.83
    POSITIVE LOGITS
    executable
    0.89
    setdefault
    0.85
    fft
    0.84
    stdlib
    0.81
    ectomy
    0.81
    rubyg
    0.80
    UseCase
    0.80
     executable
    0.79
    পাতের
    0.78
    捕捉
    0.78
    Activations Density 0.002%

    No Known Activations