© 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. 82248
    Prev
    Next
    INDEX
    Explanations

    if you

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

    This neuron activates on conditional or instructional phrases that directly address the reader, especially constructions like “If you ….”

    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
     rst
    -0.97
     רק
    -0.94
     فقط
    -0.91
     Hanya
    -0.90
     kilomet
    -0.89
    最
    -0.88
     bluz
    -0.88
    hebt
    -0.86
    ——”
    -0.85
     פשוט
    -0.84
    POSITIVE LOGITS
     any
    1.55
     still
    1.36
     want
    1.23
     found
    1.15
     anyhow
    1.12
     not
    1.10
     need
    1.05
     anyone
    0.99
     anyways
    0.98
     anybody
    0.98
    Activations Density 0.054%

    No Known Activations