© 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. 34-GEMMASCOPE-RES-131K
    7. 60072
    Prev
    Next
    INDEX
    Explanations

    programming models

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

    This neuron fires on programming‐language code tokens (especially ORM decorators/annotations and related identifiers).

    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
    θηκαν
    -0.85
    hrad
    -0.84
    urons
    -0.79
     parlamentar
    -0.78
    šk
    -0.78
     pág
    -0.76
    ʲ
    -0.75
    rehension
    -0.75
    เพียง
    -0.74
     AnyObject
    -0.74
    POSITIVE LOGITS
    cuta
    0.85
     MODEL
    0.82
    inis
    0.82
     witty
    0.80
    モデル
    0.79
     model
    0.79
    logeny
    0.77
    modelName
    0.75
     tremble
    0.75
     apprehen
    0.74
    Activations Density 0.003%

    No Known Activations