© 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. 11912
    Prev
    Next
    INDEX
    Explanations

    exasperated "don't even" phrases

    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
     with
    1.81
     với
    1.63
     (
    1.62
     dengan
    1.60
     (“
    1.59
     ("
    1.52
    ↵↵↵
    1.44
     ví
    1.44
     và
    1.41
     („
    1.41
    POSITIVE LOGITS
    चुर
    1.85
    ْت
    1.77
    Кто
    1.71
    Сред
    1.70
     Перейти
    1.69
    ЕН
    1.69
    َن
    1.67
    َد
    1.65
    Най
    1.65
    یش
    1.63
    Activations Density 0.000%

    No Known Activations