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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1113
    Prev
    Next
    INDEX
    Explanations

    wikipedia links and facts

    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
    之间
    0.88
    之間
    0.84
    に
    0.69
     †
    0.68
     
    0.65
     jokingly
    0.64
    um
    0.64
    བ
    0.63
    のお店
    0.62
    .**
    0.62
    POSITIVE LOGITS
     fresh
    1.41
     newest
    1.28
    fresh
    1.14
     latest
    1.13
     freshest
    1.13
     freshness
    0.97
    Fresh
    0.97
     majority
    0.97
    latest
    0.85
     Fresh
    0.84
    Activations Density 0.179%

    No Known Activations