© 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. 13-GEMMASCOPE-2-RES-16K
    7. 16362
    Prev
    Next
    INDEX
    Explanations

    axis label rotation

    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_13_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
     sara
    1.76
    وهات
    1.69
    ชาติ
    1.55
     kork
    1.50
    ة
    1.50
     ogen
    1.45
    ુંદર
    1.43
     Maßnahmen
    1.42
    σε
    1.41
    ྫ
    1.41
    POSITIVE LOGITS
    puesta
    2.06
    ম্ব
    1.78
    ことで
    1.77
    යු
    1.77
    न
    1.74
    Osm
    1.72
    ᆫ
    1.71
    Illustration
    1.71
    ტ
    1.69
    嘗
    1.69
    Activations Density 0.001%

    No Known Activations