© 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. 47404
    Prev
    Next
    INDEX
    Explanations

    string lowercasing and case-insensitivity

    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
     capital
    -1.56
    Capital
    -1.40
     capitalization
    -1.39
     Capital
    -1.38
    capital
    -1.36
     capitalize
    -1.26
     capitalized
    -1.16
     CAPITAL
    -1.15
    CAPITAL
    -1.08
     capitol
    -1.02
    POSITIVE LOGITS
     strtolower
    1.38
     lower
    1.36
    toLowerCase
    1.32
    lower
    1.30
     lowers
    1.20
     low
    1.20
     LOWER
    1.18
     پایین
    1.12
     LOW
    1.11
     ниж
    1.06
    Activations Density 0.034%

    No Known Activations