© 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. 17-GEMMASCOPE-2-RES-16K
    7. 926
    Prev
    Next
    INDEX
    Explanations

    domestic violence hotline

    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_17_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
    ९
    1.10
    contrib
    0.96
    जन्य
    0.93
    ८
    0.93
    тан
    0.89
     laaj
    0.87
     βά
    0.82
     view
    0.81
    Flags
    0.80
     Unidos
    0.79
    POSITIVE LOGITS
    st
    2.04
    stArray
    1.72
    xbet
    1.62
    хбет
    1.56
    ST
    1.51
    ˢ
    1.43
    <unused1439>
    1.26
    dbjc
    1.24
    stom
    1.23
    ⁄
    1.22
    Activations Density 0.790%

    No Known Activations