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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3615
    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
     程序
    1.42
    <unused977>
    1.41
     检测
    1.31
     답변
    1.30
     판단
    1.29
     フォー
    1.28
    勞
    1.27
     ইঞ্জিনিয়ার
    1.27
     금융
    1.27
     价
    1.26
    POSITIVE LOGITS
     a
    1.46
     the
    1.24
     an
    1.12
     all
    1.11
     your
    1.11
     dezelfde
    1.10
    the
    1.07
     this
    1.05
     our
    1.01
     ruim
    1.00
    Activations Density 0.064%

    No Known Activations