© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13858
    Prev
    Next
    INDEX
    Explanations

    uncomment code examples

    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
    ythe
    2.78
    amai
    2.76
    t
    2.63
    ت
    2.61
    yi
    2.60
    تش
    2.58
    yó
    2.56
     quas
    2.56
    น
    2.55
    ниях
    2.53
    POSITIVE LOGITS
    ங்கிணை
    3.12
    izar
    2.91
    ipas
    2.81
    忡
    2.80
     siku
    2.65
    short
    2.61
    ascape
    2.61
    طع
    2.60
     العربي
    2.56
    বিষ্য
    2.55
    Activations Density 0.002%

    No Known Activations