© 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. 1688
    Prev
    Next
    INDEX
    Explanations

    URLs and news sources

    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
    소가
    0.62
     rectángulo
    0.61
     refundable
    0.61
    ตำบล
    0.61
    序列
    0.58
    作
    0.57
     tangent
    0.56
    侧
    0.56
    做
    0.55
     جماعه
    0.54
    POSITIVE LOGITS
     News
    1.93
     Reuters
    1.88
    News
    1.83
     Daily
    1.82
     newspaper
    1.82
    Reuters
    1.76
    Daily
    1.75
     reporters
    1.75
     Xinhua
    1.74
     NEWS
    1.73
    Activations Density 0.542%

    No Known Activations