© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2919
    Prev
    Next
    INDEX
    Explanations

    App, Scripts, file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    <sub>
    0.87
     ܀
    0.84
    </h4>
    0.77
    例文帳に追加
    0.74
    ėj
    0.74
     ▪
    0.73
     例文帳に追加
    0.71
    ij
    0.70
     ¼
    0.70
     ƒ
    0.68
    POSITIVE LOGITS
    \
    4.83
     \
    4.61
    .\
    2.93
    ()\
    2.92
    ~\
    2.87
    ?\
    2.83
    \,\
    2.83
    '\
    2.83
    ,\
    2.81
    !\
    2.76
    Activations Density 0.329%

    No Known Activations