© 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. 16512
    Prev
    Next
    INDEX
    Explanations

    first names followed by initials

    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
     profesora
    -1.38
    Proses
    -1.36
     concurso
    -1.36
    Beberapa
    -1.30
     avantages
    -1.30
     mág
    -1.30
     protège
    -1.30
    mittag
    -1.28
     ejemplos
    -1.26
     tém
    -1.26
    POSITIVE LOGITS
     of
    1.46
     H
    1.39
     T
    1.33
     so
    1.30
     M
    1.30
     P
    1.29
     d
    1.28
     also
    1.28
     J
    1.28
    ne
    1.27
    Activations Density 0.001%

    No Known Activations