© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30206
    Prev
    Next
    INDEX
    Explanations

    specific pairings and technical terms

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

    The neuron strongly activates on dense technical specifications—especially chemical or engineering data listings with materials, formulas, and numeric values.

    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
     liquids
    -0.80
    ๅ
    -0.74
    鹹
    -0.70
    structs
    -0.70
    輩
    -0.68
     PFS
    -0.68
     Liquids
    -0.67
     enqueue
    -0.66
    ssd
    -0.66
    atillas
    -0.66
    POSITIVE LOGITS
    ঝ
    0.85
    ebay
    0.79
     acidity
    0.77
     moderna
    0.75
     combineReducers
    0.74
    jsonObject
    0.73
    extended
    0.73
     antioxidants
    0.72
     miseria
    0.72
     FILM
    0.71
    Activations Density 0.020%

    No Known Activations