© 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. 437
    Prev
    Next
    INDEX
    Explanations

    Visual Studio code snippets

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

    This neuron detects programming‐language code elements—keywords, identifiers, namespaces, type names, and punctuation in code snippets.

    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
     tapering
    -0.77
     sculpted
    -0.76
     Hayek
    -0.74
     powdery
    -0.73
     flaky
    -0.73
     transcendental
    -0.73
     Duckworth
    -0.72
     Bühnen
    -0.70
    Související
    -0.70
     convite
    -0.70
    POSITIVE LOGITS
     textView
    0.90
    dte
    0.88
     VS
    0.88
    TextView
    0.86
     abaste
    0.79
     Vs
    0.78
     Visual
    0.78
     essayer
    0.76
    reng
    0.74
     scher
    0.72
    Activations Density 0.072%

    No Known Activations