© 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. 8441
    Prev
    Next
    INDEX
    Explanations

    raw code, files, and transactions

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

    This neuron fires most strongly on very high-frequency tokens—especially those common in code and data snippets such as “raw,” “github,” URL fragments, and numeric/version strings.

    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
    fulfilled
    -0.85
    INGHAM
    -0.81
    guera
    -0.79
     shards
    -0.78
     мно
    -0.77
     faut
    -0.76
    pides
    -0.75
     caja
    -0.75
     Terbaik
    -0.74
     Fullerton
    -0.74
    POSITIVE LOGITS
    ṯ
    0.94
     Ingenie
    0.82
     -------------
    0.81
    hax
    0.78
    Frente
    0.76
     Anger
    0.75
    erse
    0.74
     ني
    0.72
    อม
    0.72
    telephone
    0.70
    Activations Density 0.009%

    No Known Activations