© 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. 66358
    Prev
    Next
    INDEX
    Explanations

    OF [document name]

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

    The neuron detects high‐level document headings or section titles, especially uppercase legal headings like “MEMORANDUM OF DECISION.”

    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
    itage
    -0.94
    enaire
    -0.86
    ולם
    -0.85
     mobilité
    -0.84
    guson
    -0.84
     rapidamente
    -0.81
    ibal
    -0.81
     émission
    -0.80
    isseur
    -0.79
     électronique
    -0.79
    POSITIVE LOGITS
     even
    1.71
    Even
    1.35
     this
    1.14
     Even
    1.13
     February
    1.03
     gennaio
    1.02
    even
    1.00
     September
    0.95
     July
    0.94
     sale
    0.93
    Activations Density 0.052%

    No Known Activations