© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4625
    Prev
    Next
    INDEX
    Explanations

    especially / effective

    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
    ↵↵
    0.99
     --
    0.96
    黄色
    0.91
    Show
    0.88
    /
    0.86
    Team
    0.86
    <start_of_image>
    0.86
    LINE
    0.85
      
    0.83
    Line
    0.83
    POSITIVE LOGITS
    <unused971>
    1.66
    <unused981>
    1.56
     וע
    1.54
    <unused710>
    1.49
    <unused316>
    1.49
    <unused967>
    1.49
    <unused1073>
    1.47
    <unused1108>
    1.45
    <unused2075>
    1.45
    <unused308>
    1.44
    Activations Density 0.002%

    No Known Activations