© 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. 1771
    Prev
    Next
    INDEX
    Explanations

    the following noun

    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
     ብቻ
    0.69
     말미
    0.67
    ثر
    0.66
     everyone
    0.65
    側
    0.65
     aside
    0.62
     behalf
    0.61
    ITING
    0.61
    =_
    0.61
    の位置
    0.60
    POSITIVE LOGITS
    mselves
    1.04
     woods
    0.91
     fridge
    0.85
     polls
    0.84
     limelight
    0.83
     wayside
    0.83
     tropics
    0.82
     gods
    0.81
     proverbial
    0.80
     nonce
    0.80
    Activations Density 0.534%

    No Known Activations