© 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. 32864
    Prev
    Next
    INDEX
    Explanations

    academic outputs and states

    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
     tejidos
    -0.98
     proveedores
    -0.97
    ATV
    -0.95
     ſmall
    -0.95
     estremamente
    -0.95
     gehabt
    -0.95
     constantemente
    -0.94
    “
    -0.94
     minerales
    -0.94
     canna
    -0.93
    POSITIVE LOGITS
    awarkan
    1.04
     hoppas
    1.02
    projeto
    1.02
     allow
    0.96
     as
    0.95
     Viitattu
    0.93
     hjälpa
    0.92
     Künst
    0.91
    Nguy
    0.90
    genöss
    0.90
    Activations Density 0.012%

    No Known Activations