© 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. 127514
    Prev
    Next
    INDEX
    Explanations

    each following noun

    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
     volverá
    -1.51
     BECAUSE
    -1.48
     fazendo
    -1.43
     لأن
    -1.38
     tendrá
    -1.36
     لأنه
    -1.35
     hará
    -1.34
    </i>
    -1.34
     correta
    -1.33
     DOING
    -1.33
    POSITIVE LOGITS
     these
    1.96
    杙
    1.56
     beker
    1.54
     benzin
    1.47
     veau
    1.47
     betek
    1.45
     lampa
    1.44
     voyageurs
    1.42
     observa
    1.41
     hitta
    1.38
    Activations Density 0.038%

    No Known Activations