© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115812
    Prev
    Next
    INDEX
    Explanations

    special characters and code

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

    This neuron detects hexadecimal byte‐escape tokens (like “xe2”, “x80”, “x9c”, etc.) representing UTF-8–encoded characters.

    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
     However
    -0.91
     invokingState
    -0.83
     strong
    -0.82
    posia
    -0.82
     provide
    -0.80
     enormous
    -0.79
     großes
    -0.79
     wzglę
    -0.79
     With
    -0.78
     gives
    -0.78
    POSITIVE LOGITS
    \
    0.89
     prada
    0.89
     Capit
    0.86
     gutt
    0.86
     laterale
    0.83
    ष्
    0.83
    mainly
    0.82
    
    0.82
    Acetone
    0.81
     byz
    0.81
    Activations Density 0.000%

    No Known Activations