© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32777
    Prev
    Next
    INDEX
    Explanations

    code syntax and identifiers

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

    This neuron fires on long, all-caps tokens (e.g. macro names, acronyms, license or header guards).

    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
    이션
    -0.74
     şöyle
    -0.73
     Ron
    -0.73
     還
    -0.71
     Süden
    -0.71
     says
    -0.70
    <blockquote>
    -0.70
    ouge
    -0.70
     CM
    -0.69
     ситуации
    -0.69
    POSITIVE LOGITS
    Pov
    0.82
    Сі
    0.81
     encapsulation
    0.80
     NSCoder
    0.79
    (___
    0.77
     wikipagina
    0.77
     appartient
    0.76
    鲫
    0.76
    ahin
    0.76
     consom
    0.75
    Activations Density 0.001%

    No Known Activations