© 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. 22795
    Prev
    Next
    INDEX
    Explanations

    ----------

    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
     to
    -2.16
    ܞ
    -2.11
    龗
    -2.09
    नलोड
    -2.08
    榇
    -2.05
    N
    -2.05
     membri
    -2.05
     nostro
    -2.03
    北部
    -2.02
    
    -2.02
    POSITIVE LOGITS
    which
    2.86
     You
    2.83
     Which
    2.81
     Presumably
    2.56
     Achieving
    2.41
     These
    2.33
     Notably
    2.28
     Undoubtedly
    2.27
    Cartney
    2.25
     Fortunately
    2.22
    Activations Density 0.021%

    No Known Activations