© 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. 1269
    Prev
    Next
    INDEX
    Explanations

    e.g., list items, contractions

    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
     sb
    2.25
    қ
    2.19
     реша
    2.14
    நுட்ப
    2.13
     ē
    2.08
    ভাগ্য
    2.07
     грн
    2.06
    力的
    2.02
     مخت
    2.02
     pr
    2.00
    POSITIVE LOGITS
    s
    4.80
    ો
    3.58
    sellers
    3.52
    o
    3.44
    ا
    3.37
    e
    3.35
    a
    3.13
    sina
    3.12
    ה
    3.11
    י
    3.11
    Activations Density 0.955%

    No Known Activations