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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99380
    Prev
    Next
    INDEX
    Explanations

    .hpp_included

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

    This neuron fires on all-caps identifier tokens (often C/C++ macro or constant names) that include 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_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
    又
    -1.63
    <blockquote>
    -1.54
    هاء
    -1.48
    to
    -1.47
     الأوروب
    -1.47
    また
    -1.46
    if
    -1.43
                
    -1.41
    he
    -1.40
    I
    -1.38
    POSITIVE LOGITS
    opinions
    1.79
    箆
    1.67
     biblia
    1.63
    茘
    1.57
     cerve
    1.54
     kupa
    1.51
     sayfa
    1.48
     parfüm
    1.48
    emissions
    1.48
     discul
    1.47
    Activations Density 0.055%

    No Known Activations