© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14578
    Prev
    Next
    INDEX
    Explanations

    python programming 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_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
     Change
    0.93
     Help
    0.91
     +
    0.89
     Or
    0.85
     Watch
    0.79
     Fund
    0.78
    +
    0.77
     or
    0.77
    でも
    0.76
     Helps
    0.75
    POSITIVE LOGITS
    த்தினை
    1.63
    <unused1563>
    1.56
    <unused698>
    1.56
     Lastly
    1.54
     keduanya
    1.54
    Lastly
    1.52
     यांचा
    1.50
    <unused1201>
    1.49
     इत्यादी
    1.49
    𒐸
    1.49
    Activations Density 0.224%

    No Known Activations