© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 65868
    Prev
    Next
    INDEX
    Explanations

    Supreme Court cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     "?"
    0.38
     nanop
    0.36
    ”—
    0.36
     ②
    0.36
     nanot
    0.36
     Justices
    0.36
    blok
    0.36
     (".
    0.36
     frapp
    0.35
    ("")
    0.35
    POSITIVE LOGITS
    <i>
    0.52
     Hernandez
    0.50
    United
    0.49
     United
    0.49
    UNITED
    0.48
     Hernández
    0.48
    Meyer
    0.46
     यूनाइटेड
    0.46
     Gomes
    0.43
     Roe
    0.42
    Activations Density 0.000%

    No Known Activations