© 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. 76081
    Prev
    Next
    INDEX
    Explanations

    letters and writing

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

    The neuron strongly activates on programming/code text (e.g. code snippets, identifiers, symbols, and numbers).

    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
     bira
    -0.81
     Brahms
    -0.81
    小
    -0.79
     Beige
    -0.76
    >+</
    -0.76
    icon
    -0.74
     Molière
    -0.74
     Opus
    -0.74
    icons
    -0.73
    Про
    -0.73
    POSITIVE LOGITS
     letters
    1.48
     letter
    1.28
    Letters
    1.23
     Letters
    1.14
    letters
    1.09
    neon
    1.09
     lettres
    1.02
     neon
    0.95
     letras
    0.95
     schreiben
    0.94
    Activations Density 0.031%

    No Known Activations