© 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. 22-GEMMASCOPE-RES-131K
    7. 32809
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     also
    -1.24
    秾
    -1.11
     décid
    -1.08
    re
    -1.06
     уровень
    -1.01
    ens
    -0.98
    本身
    -0.97
    hol
    -0.97
    </tr>
    -0.96
     als
    -0.96
    POSITIVE LOGITS
    garmin
    1.06
     to
    1.04
     فاط
    1.00
     koncentr
    0.99
     статті
    0.99
     Durchführung
    0.98
    下記
    0.98
     щоб
    0.97
     الأوروب
    0.92
    liegende
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.