© 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. 2485
    Prev
    Next
    INDEX
    Explanations

    grammar check

    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
    leftharpoons
    0.82
    <unused2218>
    0.80
    澜
    0.80
    懿
    0.78
    <unused2143>
    0.78
    ariyati
    0.78
     வீ
    0.78
    აწ
    0.78
     sabbam
    0.77
    溧
    0.77
    POSITIVE LOGITS
     GG
    2.71
    Gs
    2.62
     GA
    2.60
     GC
    2.59
    GS
    2.58
    GG
    2.57
     GS
    2.55
    GT
    2.49
    GF
    2.48
    GC
    2.48
    Activations Density 1.675%

    No Known Activations