© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3753
    Prev
    Next
    INDEX
    Explanations

    what is it like?

    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
    ্যেষ্ঠ
    2.62
    ei
    2.34
    ்ப
    2.31
    내는
    2.31
    橇
    2.23
    anjutkan
    2.23
    amai
    2.23
     кушымта
    2.16
    led
    2.14
    かで
    2.07
    POSITIVE LOGITS
    㩴
    3.34
    ೋಜನ
    3.26
    etition
    3.16
    Ⴚ
    3.09
    㕝
    3.02
    िक
    3.02
    ៌
    3.00
    ោធ
    2.91
    䥑
    2.91
    Читати
    2.90
    Activations Density 0.079%

    No Known Activations