© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4145
    Prev
    Next
    INDEX
    Explanations

    letter case conversion

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on words referring to character‐case or typography styles (e.g. uppercase, lowercase, italics, small caps, underscores).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    óbal
    -0.85
    trim
    -0.82
     Trim
    -0.78
     trim
    -0.78
     TRIM
    -0.75
    LineColor
    -0.75
     yardım
    -0.74
     Böyle
    -0.74
     quả
    -0.72
    岡
    -0.71
    POSITIVE LOGITS
     letters
    1.48
    Letters
    1.05
    切换
    1.02
     conversion
    1.00
     letter
    1.00
     lettering
    0.99
    letters
    0.98
     capital
    0.98
     Letters
    0.93
     lettere
    0.93
    Activations Density 0.031%

    No Known Activations