© 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. 16666
    Prev
    Next
    INDEX
    Explanations

    put back together

    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
    orant
    -1.19
     this
    -1.16
    ectado
    -1.11
     повече
    -1.09
    werve
    -1.06
     scén
    -1.05
     délib
    -1.05
     siapa
    -1.05
     Weiterbildung
    -1.05
     cuál
    -1.04
    POSITIVE LOGITS
     carefully
    1.17
     صحیح
    1.16
     properly
    1.12
     Bunga
    1.05
    ini
    1.05
     обратно
    1.04
     vervol
    1.03
     CITED
    1.02
    🤑
    1.01
     installation
    1.00
    Activations Density 0.009%

    No Known Activations