© 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. 32681
    Prev
    Next
    INDEX
    Explanations

    file names and code snippets

    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
    ěte
    -1.07
     reacties
    -1.05
     Litu
    -1.05
    lieder
    -1.02
    jść
    -1.02
     saken
    -1.02
     haup
    -1.01
    簓
    -1.00
     nasz
    -1.00
     Erl
    -1.00
    POSITIVE LOGITS
     to
    1.41
     R
    1.14
     now
    1.07
     Grüßen
    1.01
     Schlafzimmer
    0.99
     doesn
    0.96
     δὲ
    0.96
     also
    0.95
     муніципалі
    0.94
     at
    0.94
    Activations Density 0.013%

    No Known Activations