© 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. 127656
    Prev
    Next
    INDEX
    Explanations

    industry associations

    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
     images
    -1.27
    ͂
    -1.20
     блюдо
    -1.17
    disposing
    -1.16
     nutrisi
    -1.16
     也
    -1.14
     الجلد
    -1.13
     растения
    -1.12
    People
    -1.11
    family
    -1.10
    POSITIVE LOGITS
     membership
    1.51
     representing
    1.43
    ִּ
    1.39
    membership
    1.34
     Representing
    1.23
     étages
    1.22
    representing
    1.20
    ַּ
    1.20
    ּוֹ
    1.20
     industry
    1.18
    Activations Density 0.040%

    No Known Activations