© 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. 64281
    Prev
    Next
    INDEX
    Explanations

    what is

    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
     would
    -1.10
     srdce
    -1.07
    Durata
    -1.04
     takich
    -1.01
     jednej
    -1.00
     boîtier
    -0.98
     таких
    -0.94
     either
    -0.94
     pierwszym
    -0.94
     necesar
    -0.92
    POSITIVE LOGITS
    ?
    1.67
     in
    1.26
     when
    1.16
    YTE
    1.05
    кумулятор
    1.02
     doing
    1.02
     then
    1.01
    设立
    1.01
     púb
    1.00
     arbeta
    1.00
    Activations Density 0.038%

    No Known Activations