© 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. 10207
    Prev
    Next
    INDEX
    Explanations

    New York Times links

    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
    ould
    1.30
    Ç
    1.29
    
    1.28
     เ
    1.27
    Ire
    1.26
    Ee
    1.25
     ต้อง
    1.24
    Ow
    1.23
    mdash
    1.22
    REAM
    1.20
    POSITIVE LOGITS
     primo
    0.90
    着
    0.89
     teniendo
    0.88
     relativo
    0.87
     autora
    0.87
     buona
    0.85
     telefone
    0.85
     letra
    0.85
     subir
    0.85
     relativa
    0.85
    Activations Density 0.010%

    No Known Activations