© 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. 6884
    Prev
    Next
    INDEX
    Explanations

    negated verbs

    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
    縢
    -2.36
    
    -2.28
     pessoais
    -2.23
    糨
    -2.20
    阏
    -2.20
     mantém
    -2.14
    蹰
    -2.13
     ensaio
    -2.13
     gän
    -2.11
     играет
    -2.08
    POSITIVE LOGITS
     and
    2.53
     be
    2.47
    т
    2.33
    й
    2.25
    न
    2.19
    но
    2.17
    л
    2.11
    н
    2.06
    </td>
    2.05
    ी
    2.00
    Activations Density 0.008%

    No Known Activations