© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12376
    Prev
    Next
    INDEX
    Explanations

    LaTeX geometry settings

    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
    ت
    3.09
    hive
    2.87
    Con
    2.58
     crook
    2.55
    s
    2.54
    uates
    2.52
     Con
    2.46
    screw
    2.36
    تف
    2.33
    жно
    2.29
    POSITIVE LOGITS
    스테
    3.18
    ্প
    2.87
    endente
    2.83
    endenti
    2.83
     golongan
    2.76
     soglas
    2.69
    틋
    2.66
     stimmen
    2.64
    ılık
    2.62
    ী
    2.59
    Activations Density 0.005%

    No Known Activations