© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9337
    Prev
    Next
    INDEX
    Explanations

    code examples and technical terms

    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
    <h1>
    0.98
     раза
    0.95
     PRA
    0.85
     สูตร
    0.84
     then
    0.82
     Cr
    0.81
     
    0.80
     но
    0.79
    г
    0.79
     Ama
    0.79
    POSITIVE LOGITS
    oded
    1.52
    𐰼
    1.52
    ᚄ
    1.51
    ꞎ
    1.50
    <unused1893>
    1.49
    <unused2022>
    1.47
    𐰰
    1.47
    λή
    1.46
    ꗟ
    1.45
    𐰑
    1.42
    Activations Density 0.000%

    No Known Activations