© 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. 10601
    Prev
    Next
    INDEX
    Explanations

    closing parentheses `))`

    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
    մ
    0.85
    醉
    0.84
     উর্দু
    0.83
     brandy
    0.83
     rượu
    0.82
     চীনা
    0.80
    ขั้น
    0.79
     taff
    0.79
    餡
    0.77
    alcoholic
    0.77
    POSITIVE LOGITS
     Volleyball
    1.57
     setter
    1.38
     volleyball
    1.35
     libero
    1.34
     digs
    1.27
     Beach
    1.25
     hitter
    1.22
     dig
    1.21
     Dig
    1.18
    Dig
    1.17
    Activations Density 0.051%

    No Known Activations