© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1067
    Prev
    Next
    INDEX
    Explanations

    languages and concepts

    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_17_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
     respectivos
    1.04
    getProperty
    0.95
     bija
    0.94
     ит
    0.92
     आइकॉन
    0.91
    └──
    0.90
    υσ
    0.90
     Specialties
    0.88
     respectivas
    0.87
     quanto
    0.87
    POSITIVE LOGITS
    only
    2.13
     only
    2.10
     فقط
    1.99
     только
    1.99
     seulement
    1.86
     ONLY
    1.82
    Only
    1.78
    仅
    1.78
     hanya
    1.75
    ONLY
    1.75
    Activations Density 0.346%

    No Known Activations