© 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. 34-GEMMASCOPE-RES-131K
    7. 3485
    Prev
    Next
    INDEX
    Explanations

    code keywords and types

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     just
    -1.24
     as
    -1.23
     if
    -1.20
     without
    -1.16
     because
    -1.14
     get
    -1.03
     at
    -1.02
     both
    -1.02
     岁
    -1.00
     new
    -0.98
    POSITIVE LOGITS
     patienter
    1.24
    豋
    1.17
     apprécier
    1.13
     osoby
    1.13
     embaj
    1.11
     masaje
    1.10
     meub
    1.09
     offrir
    1.08
     этого
    1.07
     نیز
    1.07
    Activations Density 0.010%

    No Known Activations