© 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. 57006
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    躊
    -0.85
     زدن
    -0.79
    Tél
    -0.79
     Weiterbildung
    -0.78
    REGUL
    -0.75
     höheren
    -0.75
     pourra
    -0.74
    峥
    -0.73
    上級
    -0.73
    caccio
    -0.73
    POSITIVE LOGITS
     sclerosis
    1.00
     dioxide
    0.99
     "-
    0.94
     letto
    0.94
    Ꮋ
    0.87
    WINDOWS
    0.87
     zni
    0.85
     ness
    0.85
     ware
    0.84
     aureus
    0.81
    Activations Density 0.125%

    No Known Activations