© 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. 73666
    Prev
    Next
    INDEX
    Explanations

    names of artists and celebrities

    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
     its
    -1.84
     your
    -1.33
    様な
    -1.23
    its
    -1.15
     like
    -1.09
     one
    -1.09
    場所で
    -1.06
     striving
    -1.05
     технологі
    -1.05
     their
    -1.04
    POSITIVE LOGITS
     who
    1.68
     himself
    1.38
    <bos>
    1.30
    oused
    1.27
    ardized
    1.27
    ,_
    1.24
     mwenye
    1.21
    kungen
    1.17
     الشخصية
    1.16
     telefónica
    1.16
    Activations Density 0.040%

    No Known Activations