© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118678
    Prev
    Next
    INDEX
    Explanations

    sole traders or soleus muscle

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

    The neuron activates for the word "sole" and related forms, particularly when referring to a type of business entity, muscle, or fish.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     ситуа
    -0.72
    SYMBOL
    -0.69
    センス
    -0.68
     đoàn
    -0.68
    ühen
    -0.67
    gements
    -0.66
     riddles
    -0.66
     Sarac
    -0.66
    rauch
    -0.66
     faults
    -0.65
    POSITIVE LOGITS
     proprietor
    1.39
     proprietors
    1.29
     propriet
    1.27
     purpose
    1.23
     trader
    1.02
    mates
    1.02
     PURPOSE
    1.00
     Propriet
    1.00
     survivor
    1.00
    purpose
    0.98
    Activations Density 0.013%

    No Known Activations