© 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. 14599
    Prev
    Next
    INDEX
    Explanations

    echo completion messages

    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
     '
    1.44
    sz
    1.41
    sb
    1.41
     teman
    1.36
    tk
    1.34
    শিয়া
    1.32
     Issue
    1.31
     Index
    1.29
     '&
    1.26
    tay
    1.26
    POSITIVE LOGITS
    compassing
    1.78
    primarily
    1.72
    capture
    1.63
    bodied
    1.59
    Coastal
    1.57
    captivity
    1.54
    commonly
    1.52
    northern
    1.50
    Matthew
    1.49
     discernible
    1.49
    Activations Density 0.000%

    No Known Activations