© 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. 127758
    Prev
    Next
    INDEX
    Explanations

    action verbs followed by articles

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     it
    -1.40
     trabajar
    -1.38
     there
    -1.33
    พ์
    -1.30
     його
    -1.30
    日で
    -1.29
     sabid
    -1.28
    ουργ
    -1.27
    洐
    -1.26
    巨大的
    -1.23
    POSITIVE LOGITS
     the
    2.05
     a
    1.58
    of
    1.41
    臵
    1.30
    неров
    1.22
     Перейти
    1.20
    ご連絡
    1.17
     torner
    1.16
     DOES
    1.16
     télécommande
    1.16
    Activations Density 0.020%

    No Known Activations