© 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. 70239
    Prev
    Next
    INDEX
    Explanations

    not found or defined

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

    The neuron primarily activates on the negation “not,” detecting instances of that word.

    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
    仅
    -1.05
     only
    -1.04
     فقط
    -0.99
    зил
    -0.99
    は
    -0.96
     ONLY
    -0.95
    faits
    -0.95
    gén
    -0.94
     лише
    -0.94
    нули
    -0.94
    POSITIVE LOGITS
     found
    2.25
     allowed
    1.59
     recognized
    1.39
    found
    1.39
     properly
    1.39
     implemented
    1.38
     supported
    1.34
     belong
    1.34
     available
    1.33
     enough
    1.29
    Activations Density 0.059%

    No Known Activations