© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12099
    Prev
    Next
    INDEX
    Explanations

    real-world implementation contexts

    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
    单独
    1.22
    ód
    1.19
    偌
    1.18
     phía
    1.18
    ńcz
    1.17
     ficando
    1.17
    穿着
    1.15
     άλλο
    1.15
    苍
    1.14
    通风
    1.12
    POSITIVE LOGITS
     RIA
    0.89
     desir
    0.85
     hebdom
    0.80
    TOP
    0.79
    াধিক
    0.79
    iones
    0.78
    ioi
    0.77
    WORDS
    0.76
    BACK
    0.76
    addElement
    0.76
    Activations Density 0.179%

    No Known Activations