© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11003
    Prev
    Next
    INDEX
    Explanations

    microsoft learn documentation links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     Análisis
    1.56
    員の
    1.55
    員
    1.54
    बिया
    1.53
     selamat
    1.49
    atiche
    1.48
     nieuwe
    1.48
    baru
    1.48
     neue
    1.47
     Zasshi
    1.47
    POSITIVE LOGITS
     也
    1.75
    ாலை
    1.70
     ι
    1.65
     ‍
    1.61
     通常
    1.60
     在
    1.58
    在此
    1.57
    忱
    1.57
     ғ
    1.55
     为了
    1.55
    Activations Density 0.001%

    No Known Activations