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. 3776
    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
     agreg
    2.02
    𝗿
    1.95
    राने
    1.87
    ہنی
    1.86
    dest
    1.85
    пли
    1.84
     gest
    1.83
     agrega
    1.83
    𝘂
    1.82
    hores
    1.77
    POSITIVE LOGITS
    uppercase
    1.99
     alphabet
    1.91
    ೭
    1.85
     letters
    1.83
    ্টে
    1.83
    wheels
    1.76
    DEFGHI
    1.74
    ೮
    1.73
    Ⅽ
    1.67
    렀
    1.67
    Activations Density 0.398%

    No Known Activations