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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2443
    Prev
    Next
    INDEX
    Explanations

    click the

    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
    竟然
    0.80
    有些
    0.80
    そういう
    0.80
    ája
    0.79
    纂
    0.77
    那样
    0.77
    They
    0.76
    <unused206>
    0.72
    emt
    0.70
    那么多
    0.69
    POSITIVE LOGITS
     our
    2.05
     either
    1.81
    我们的
    1.53
    我們的
    1.44
     any
    1.42
     nuestro
    1.41
     unsere
    1.40
     আমাদের
    1.37
     nossos
    1.37
     unseren
    1.37
    Activations Density 0.774%

    No Known Activations