© 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. 83918
    Prev
    Next
    INDEX
    Explanations

    questions starting with should

    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
    卺
    -2.73
    沨
    -2.56
    刄
    -2.55
    龉
    -2.52
    禟
    -2.39
    pfung
    -2.38
    圌
    -2.33
     hır
    -2.33
    ’
    -2.31
    樒
    -2.30
    POSITIVE LOGITS
    t
    2.92
    (
    2.81
     be
    2.77
    </td>
    2.69
     }))
    2.53
    睺
    2.50
    ?
    2.48
    но
    2.38
    т
    2.36
    </h6>
    2.28
    Activations Density 0.041%

    No Known Activations