© 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. 1433
    Prev
    Next
    INDEX
    Explanations

    sidebar menu panel nav

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

    The neuron fires on programming-style tokens (identifiers, keywords, imports, HTML/XML tags) and thus flags snippets of source code.

    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
    ثیر
    -0.82
    Hud
    -0.80
     edile
    -0.79
     normalt
    -0.77
    Kommentare
    -0.76
    右手
    -0.74
    　　《
    -0.74
    Роман
    -0.73
     galletas
    -0.73
    María
    -0.73
    POSITIVE LOGITS
     sidebar
    1.09
     Schatten
    0.84
     Pierson
    0.83
    sidebar
    0.82
     Drawer
    0.80
     Sidebar
    0.78
    ждений
    0.75
     листь
    0.75
     Collapse
    0.73
     doccia
    0.73
    Activations Density 0.006%

    No Known Activations