© 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. 7-GEMMASCOPE-2-RES-16K
    7. 610
    Prev
    Next
    INDEX
    Explanations

    Nevada

    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_7_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
    iate
    2.31
    <bos>
    2.21
    evice
    2.18
    ാ
    2.13
    eal
    2.03
    ы
    1.98
    iat
    1.92
    ea
    1.91
    hung
    1.90
    iop
    1.87
    POSITIVE LOGITS
    स्यों
    2.05
     paraît
    2.00
    裟
    1.96
     Grenzen
    1.96
    彡
    1.92
     बारे
    1.91
    ประสบการณ์
    1.89
    ীষ
    1.88
     Harr
    1.88
    ৪৪
    1.86
    Activations Density 0.252%

    No Known Activations