© 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. 47191
    Prev
    Next
    INDEX
    Explanations

    practice something specific

    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
     practice
    -1.13
     experience
    -0.94
     investigaciones
    -0.90
    花板
    -0.86
     study
    -0.85
    いっぱ
    -0.85
     النص
    -0.85
     bes
    -0.85
    见识
    -0.85
    喰
    -0.84
    POSITIVE LOGITS
     with
    1.45
     using
    1.34
     until
    1.18
     what
    1.16
     on
    1.02
     makes
    0.98
     making
    0.98
     some
    0.97
     voulais
    0.96
     getting
    0.94
    Activations Density 0.011%

    No Known Activations