© 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. 5280
    Prev
    Next
    INDEX
    Explanations

    Look for specific items

    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
    刀
    0.95
    やや
    0.95
     coalgebra
    0.90
    剑
    0.83
    옮
    0.81
    ソード
    0.81
    꽃
    0.79
     شراب
    0.79
    กลับ
    0.79
    ücke
    0.78
    POSITIVE LOGITS
    ००
    1.47
    ۰۰
    1.40
     hundred
    1.40
    FFFF
    1.35
     thousand
    1.35
    hundred
    1.33
     उत्
    1.32
    FFFFFF
    1.32
    YYYY
    1.30
    ﺤ
    1.27
    Activations Density 0.196%

    No Known Activations