© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72055
    Prev
    Next
    INDEX
    Explanations

    painstaking, excruciating, painfully, exceedingly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "
    -2.95
    ;
    -2.44
     If
    -2.17
    </i>
    -1.97
     THEIR
    -1.86
    是
    -1.86
     και
    -1.83
    媽
    -1.79
    <i>
    -1.79
     でも
    -1.78
    POSITIVE LOGITS
    pulseira
    2.70
     zumal
    2.42
    曏
    2.42
    鲞
    2.34
     womit
    2.34
     wodurch
    2.25
    畱
    2.20
     новые
    2.17
    纡
    2.16
    嚒
    2.13
    Activations Density 0.005%

    No Known Activations