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. 3903
    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
    겉
    1.04
    <unused2145>
    1.03
     elementType
    1.02
    ിയുടെ
    1.02
     얼굴
    1.01
     정말
    1.01
    퍁
    1.01
    것도
    1.01
     レイ
    1.00
    刄
    0.99
    POSITIVE LOGITS
     ou
    1.24
     oder
    1.08
     or
    1.06
     konkur
    0.95
     или
    0.95
     alternativa
    0.92
     atau
    0.90
     või
    0.90
     eller
    0.89
     if
    0.89
    Activations Density 0.125%

    No Known Activations