© 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. 55626
    Prev
    Next
    INDEX
    Explanations

    naturally occurring

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

    The neuron detects occurrences of the phrase “naturally occurring.”

    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
    ট
    -0.95
     annoyance
    -0.94
    nehm
    -0.87
     ACTUAL
    -0.85
    étaire
    -0.85
    izer
    -0.85
    的不同
    -0.85
     stipulations
    -0.85
     APPROPRI
    -0.84
     momentan
    -0.83
    POSITIVE LOGITS
     occurring
    1.94
     available
    1.38
     accepted
    1.23
     Occur
    1.13
     occurs
    1.12
     used
    1.12
     occur
    1.07
     happening
    1.06
     występu
    1.05
     occ
    1.02
    Activations Density 0.071%

    No Known Activations