© 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. 60027
    Prev
    Next
    INDEX
    Explanations

    technical code snippets

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

    This neuron is triggered by the “.” token used in code, i.e. the periods separating package and class or method qualifiers.

    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
     clearer
    -0.86
     recrystal
    -0.77
     soon
    -0.77
    ppur
    -0.76
    isso
    -0.75
    âmara
    -0.75
    rikt
    -0.75
    🥌
    -0.73
    wikkel
    -0.72
    鍔
    -0.72
    POSITIVE LOGITS
     heeled
    0.86
     content
    0.86
     oscuridad
    0.82
    vied
    0.81
    liang
    0.79
     oxidation
    0.77
    Shaders
    0.77
     아
    0.77
     status
    0.77
    status
    0.76
    Activations Density 0.002%

    No Known Activations