© 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. 32797
    Prev
    Next
    INDEX
    Explanations

    techniques and procedures

    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
     žena
    -1.09
     žel
    -1.05
     lỗi
    -1.03
    Etimo
    -1.02
    lierung
    -1.00
    unjungi
    -1.00
    喲
    -0.98
    StandardCharsets
    -0.97
     missing
    -0.97
    すな
    -0.97
    POSITIVE LOGITS
     to
    1.93
     as
    1.45
     technology
    1.35
     techniques
    1.27
     вместо
    1.24
     instead
    1.16
     rather
    1.16
     technique
    1.16
     principles
    1.14
     anstatt
    1.14
    Activations Density 0.205%

    No Known Activations