© 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. 45689
    Prev
    Next
    INDEX
    Explanations

    logistic regression

    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
    
    -3.31
     we
    -3.06
    Ꮉ
    -3.00
    
    -3.00
     unſ
    -3.00
    砹
    -2.92
    纐
    -2.84
    ᐕ
    -2.81
    赑
    -2.75
    螄
    -2.70
    POSITIVE LOGITS
    孓
    2.80
    鉭
    2.47
     最
    2.45
    Only
    2.45
    While
    2.38
    They
    2.27
    Like
    2.25
     sagging
    2.25
    When
    2.19
    Just
    2.19
    Activations Density 0.001%

    No Known Activations