© 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. 24920
    Prev
    Next
    INDEX
    Explanations

    conversational introductions

    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
     and
    -1.51
    inverno
    -0.98
    ά
    -0.92
    chemise
    -0.89
    ethene
    -0.86
     tille
    -0.84
     temperatuur
    -0.84
     egna
    -0.84
    ísima
    -0.83
     to
    -0.82
    POSITIVE LOGITS
    実は
    1.23
    atiles
    1.13
    ОВ
    1.03
     récents
    1.02
     informes
    1.02
     situaciones
    1.02
    有个
    1.02
     христиан
    0.99
    关于
    0.98
     Mejora
    0.94
    Activations Density 0.028%

    No Known Activations