© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9502
    Prev
    Next
    INDEX
    Explanations

    Python comments

    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
    ᅵ
    2.88
    ून
    2.85
    𝙴
    2.75
    নে
    2.72
    ʸ
    2.70
    political
    2.62
    σκο
    2.61
    𝐨
    2.61
    Idioma
    2.59
    ˧
    2.55
    POSITIVE LOGITS
    ه
    5.45
    a
    4.88
    i
    4.86
    ಿ
    3.95
    ۰
    3.78
    ‌ی
    3.43
    هي
    3.39
    ‌ای
    3.38
    ા
    3.34
    ി
    3.25
    Activations Density 0.401%

    No Known Activations