© 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. 1258
    Prev
    Next
    INDEX
    Explanations

    refusal of harmful requests

    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
    udir
    0.84
    pand
    0.76
    ivate
    0.71
    álni
    0.70
    -
    0.70
    antam
    0.69
     stoi
    0.67
    (
    0.67
    "
    0.65
    jom
    0.65
    POSITIVE LOGITS
    s
    2.16
    €™
    1.55
    Tis
    1.54
    sG
    1.48
    ’’’’
    1.43
    ਤੇ
    1.37
    র
    1.34
    ا
    1.33
    sse
    1.32
    ㅅ
    1.31
    Activations Density 0.459%

    No Known Activations