© 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. 32796
    Prev
    Next
    INDEX
    Explanations

    future probability auxiliaries

    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
     médic
    -1.02
    skap
    -0.96
     bolsillos
    -0.95
     rusak
    -0.93
     khawatir
    -0.93
     spagno
    -0.92
     magasiner
    -0.91
    новид
    -0.91
     cielos
    -0.91
     flott
    -0.90
    POSITIVE LOGITS
     likely
    1.24
     new
    1.08
     potential
    1.02
     be
    0.96
     spring
    0.95
     offer
    0.92
     joins
    0.89
     erstmals
    0.87
    onents
    0.86
     cuya
    0.85
    Activations Density 0.044%

    No Known Activations