© 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. 30128
    Prev
    Next
    INDEX
    Explanations

    code variables and functions

    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
    Negative Logits
     الشه
    -0.86
    Cancell
    -0.86
    য়া
    -0.85
     本店
    -0.85
     vague
    -0.84
    KURZ
    -0.83
    länger
    -0.82
     Cameroun
    -0.81
     allé
    -0.81
     himſelf
    -0.80
    POSITIVE LOGITS
     which
    1.11
     find
    0.91
    indexOf
    0.83
     menemukan
    0.82
    тон
    0.82
     Math
    0.81
     lyck
    0.77
     cerevisiae
    0.77
     kesalahan
    0.75
     thanh
    0.75
    Activations Density 0.011%

    No Known Activations