Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3802
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    𝒾
    1.99
    렇게
    1.84
    бота
    1.80
    𝓉
    1.74
    ൃശ
    1.74
    ისი
    1.72
    ant
    1.67
    ী
    1.66
    伎
    1.66
    rü
    1.65
    POSITIVE LOGITS
     priced
    2.24
     staffed
    1.81
     อ่ะ
    1.76
    ๘
    1.75
    OnUiThread
    1.73
    ๖
    1.70
     faudrait
    1.69
     ched
    1.68
     haired
    1.66
     sophistic
    1.66
    Activations Density 0.556%

    No Known Activations