© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13463
    Prev
    Next
    INDEX
    Explanations

    voice leading, Force Majeure, Lifetime

    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
    गिन
    2.82
     способов
    2.75
    ют
    2.62
    љ
    2.55
    哪些
    2.48
     பாபிலோ
    2.46
    après
    2.41
     incluso
    2.38
    <unused1103>
    2.36
     לפי
    2.35
    POSITIVE LOGITS
    teri
    1.70
    kehr
    1.70
    hiana
    1.69
    دا
    1.61
    teral
    1.57
    terase
    1.56
    pike
    1.56
    داً
    1.55
    م
    1.49
    প্তরের
    1.49
    Activations Density 0.018%

    No Known Activations