© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217995
    Prev
    Next
    INDEX
    Explanations

    no turkey stuffing

    np_acts-logits-general · gemini-2.5-flash-lite

    starter, plt, antibodies, former

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    кий
    0.43
     GridPane
    0.42
     agregado
    0.41
    كه
    0.41
    ของผู้
    0.41
    蟋
    0.41
     mongodb
    0.40
     atta
    0.40
    ﹀
    0.39
     ն
    0.39
    POSITIVE LOGITS
    treat
    0.55
    x
    0.52
    _{+
    0.49
    beat
    0.48
    f
    0.48
    hq
    0.47
    cooking
    0.47
    discuss
    0.47
    yu
    0.47
    medical
    0.47
    Activations Density 0.000%

    No Known Activations