© 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. 32793
    Prev
    Next
    INDEX
    Explanations

    team status and outlook

    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
    ദ
    -1.18
    ଵ
    -1.15
    rifft
    -1.06
     "]";
    -1.01
    licazione
    -1.01
    ᶜ
    -1.00
     宮
    -1.00
     decisión
    -0.99
     dzisiaj
    -0.98
    范文
    -0.96
    POSITIVE LOGITS
     year
    1.53
     season
    1.18
     we
    1.18
     success
    1.17
     
    1.14
     this
    1.09
     achievable
    1.07
     année
    1.06
     They
    1.03
    Expectations
    1.02
    Activations Density 0.045%

    No Known Activations