© 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. 5749
    Prev
    Next
    INDEX
    Explanations

    suicide prevention or danger authorities

    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
     MAKEINTRESOURCE
    1.73
    GET
    1.67
     pin
    1.63
    ্স্ট
    1.63
     coût
    1.62
    getChildren
    1.61
     ஆகும்
    1.59
    "]["
    1.57
     peligro
    1.56
     зарегистри
    1.55
    POSITIVE LOGITS
    笠
    2.04
    締
    1.74
     contented
    1.68
    ファー
    1.66
     entgegen
    1.65
    胱
    1.60
     الماض
    1.55
    backers
    1.51
    verse
    1.49
    ेंटल
    1.48
    Activations Density 0.019%

    No Known Activations