© 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. 10-GEMMASCOPE-RES-131K
    7. 15760
    Prev
    Next
    INDEX
    Explanations

    workflow

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    訁
    -1.95
     $
    -1.95
    ).
    -1.91
    \
    -1.83
    泚
    -1.81
    genodigd
    -1.80
    2
    -1.79
    –
    -1.78
    \&
    -1.70
    合う
    -1.66
    POSITIVE LOGITS
     borsa
    2.00
    嗵
    1.98
    ắ
    1.92
    喁
    1.92
     analisis
    1.92
     они
    1.88
    婓
    1.88
    andale
    1.76
    醯
    1.76
    蚍
    1.73
    Activations Density 0.002%

    No Known Activations