© 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-16K
    7. 2274
    Prev
    Next
    INDEX
    Explanations

    opening parenthesis (`(` or `（`)

    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
    hFile
    1.24
    )¶
    1.20
    ၡ
    1.19
    <unused391>
    1.18
    ၤ
    1.18
    ပါတယ်
    1.14
    忄
    1.13
    ပြော
    1.11
    )|^
    1.10
    ம்தா
    1.09
    POSITIVE LOGITS
     (
    5.10
    （
    4.15
    (
    4.03
     ("
    3.92
     (“
    3.84
     ([
    3.83
     （
    3.74
     ('
    3.59
     (<
    3.59
     ((
    3.55
    Activations Density 1.452%

    No Known Activations