© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14227
    Prev
    Next
    INDEX
    Explanations

    introducing clauses or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ottimo
    0.94
    定番
    0.90
     及
    0.88
     lovely
    0.87
     joys
    0.86
     mighty
    0.86
     beserta
    0.84
     itp
    0.83
     etc
    0.81
    govt
    0.80
    POSITIVE LOGITS
     whereby
    0.98
    ವಾಗ
    0.95
     כאשר
    0.95
     bahwa
    0.89
    <unused2173>
    0.89
     lorsque
    0.88
    คนที่
    0.85
    |(
    0.84
     aqueles
    0.84
     organizations
    0.84
    Activations Density 0.399%

    No Known Activations