© 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. 14502
    Prev
    Next
    INDEX
    Explanations

    code formatting with backticks

    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
    ee
    3.01
    此之外
    2.90
    ees
    2.86
    ক্ষ
    2.81
    ੀ
    2.80
    eee
    2.76
    ிருஷ்
    2.75
    mina
    2.67
    eh
    2.67
    ighter
    2.66
    POSITIVE LOGITS
    Incoming
    3.41
    ﮄ
    3.19
    на
    3.03
    ਆ
    2.94
    Editors
    2.91
    笆
    2.78
    ঃখ
    2.76
    깐
    2.75
    м
    2.66
    дзен
    2.66
    Activations Density 0.113%

    No Known Activations