© 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. 8475
    Prev
    Next
    INDEX
    Explanations

    fighter jets and squadrons

    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
    ?
    -1.49
    </strong>
    -1.47
    财务
    -1.31
     femelle
    -1.30
     icône
    -1.26
     is
    -1.25
    THE
    -1.25
     collega
    -1.24
    ↵↵↵↵↵↵↵
    -1.20
    rentiel
    -1.20
    POSITIVE LOGITS
     recibiendo
    1.52
    6
    1.49
    譬
    1.46
     fisuras
    1.44
    ጪ
    1.43
     consciência
    1.42
     vantagem
    1.41
     个人
    1.38
     realizando
    1.38
     zapach
    1.30
    Activations Density 0.015%

    No Known Activations