© 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. 10669
    Prev
    Next
    INDEX
    Explanations

    call 911 or local emergency number

    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
    ্শন
    2.54
    ்ட
    2.39
    ि
    2.33
    রফ
    2.27
    াগ
    2.24
    տ
    2.19
     counties
    2.16
    ே
    2.13
    ेंस
    2.11
    ोम
    2.10
    POSITIVE LOGITS
    siye
    2.50
    sman
    2.29
    ౖ
    2.14
    akeda
    2.11
    والفقار
    2.09
    চারের
    2.08
    tif
    2.07
    ckt
    2.06
    ̐
    2.05
    びに
    2.03
    Activations Density 0.003%

    No Known Activations