© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 569
    Prev
    Next
    INDEX
    Explanations

    digits and arithmetic operations

    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
     ¾
    0.63
    <em>
    0.60
     “…
    0.60
     meet
    0.59
     ½
    0.59
     Meet
    0.58
    meet
    0.57
     glorified
    0.56
    Meet
    0.52
     […]
    0.52
    POSITIVE LOGITS
    <unused1696>
    0.69
    <unused1101>
    0.64
    <unused1881>
    0.64
    <unused570>
    0.63
     अभिकारक
    0.62
     صہی
    0.61
    ⵕ
    0.61
     :+:
    0.61
    കളും
    0.60
     строка
    0.60
    Activations Density 0.145%

    No Known Activations