© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7140
    Prev
    Next
    INDEX
    Explanations

    A/B test

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     歴史
    2.72
     yeter
    2.60
     mengembangkan
    2.57
     Исто
    2.54
     눌
    2.52
     Amplifier
    2.50
     لأ
    2.49
     hospitales
    2.49
    ווע
    2.49
     Inspirational
    2.48
    POSITIVE LOGITS
    <em>
    0.46
    <strong>
    0.43
     +
    0.42
     front
    0.36
    vis
    0.36
     -
    0.34
    Lato
    0.34
     \
    0.33
    urek
    0.31
    visit
    0.31
    Activations Density 0.016%

    No Known Activations