© 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. 13685
    Prev
    Next
    INDEX
    Explanations

    either/or alternatives

    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
    𝐞
    2.31
    ever
    2.31
    eos
    2.27
     suspected
    2.24
    e
    2.19
    fore
    2.19
    ei
    2.18
    eip
    2.17
    গুপ্ত
    2.17
    velt
    2.16
    POSITIVE LOGITS
    Og
    2.78
     заход
    2.73
    зяржа
    2.57
    з
    2.57
    ợi
    2.55
    SEQU
    2.54
     τὸν
    2.50
    빅
    2.49
    ра
    2.49
    agascar
    2.49
    Activations Density 0.006%

    No Known Activations