© 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. 98898
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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
    Negative Logits
     misguided
    -1.91
     gets
    -1.82
     should
    -1.77
     makes
    -1.73
     —
    -1.67
    O
    -1.66
     needs
    -1.64
     If
    -1.63
     blatantly
    -1.62
     /
    -1.59
    POSITIVE LOGITS
    ⑊
    2.33
    ჻
    2.27
    不得不说
    2.17
    ⩴
    2.06
    鹟
    2.05
    嵛
    1.99
    卺
    1.97
    粜
    1.97
     ír
    1.95
    曁
    1.95
    Activations Density 0.028%

    No Known Activations