© 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. 10-GEMMASCOPE-RES-131K
    7. 127481
    Prev
    Next
    INDEX
    Explanations

    code snippets and names

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

    This neuron detects CamelCase identifiers (multi-word class or method names with internal capital letters).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </b>
    -2.95
    and
    -2.86
    并将
    -2.73
    {
    -2.55
     và
    -2.45
    并且
    -2.41
     и
    -2.39
    over
    -2.36
    *
    -2.31
    ⡑
    -2.31
    POSITIVE LOGITS
    왘
    2.73
    臜
    2.67
    嵛
    2.67
     harten
    2.59
    嚒
    2.58
    ᐠ
    2.48
    
    2.47
    摳
    2.45
    idlertid
    2.41
     baskılı
    2.38
    Activations Density 0.001%

    No Known Activations