© 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. 119191
    Prev
    Next
    INDEX
    Explanations

    bath and cooling

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

    The neuron is sensitive to numerical and quantitative terms—numbers, units, and parameter names—typical of technical or scientific measurement contexts.

    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
    KindOfClass
    -0.88
    uram
    -0.79
     evaluar
    -0.77
     ahorrar
    -0.77
     twe
    -0.76
    烧
    -0.75
     detox
    -0.74
    mtliche
    -0.73
    esz
    -0.73
    íze
    -0.72
    POSITIVE LOGITS
     bath
    2.39
    bath
    1.84
     Bath
    1.84
    Bath
    1.74
     baths
    1.71
     bain
    1.54
    BATH
    1.46
     BATH
    1.36
     baño
    1.33
     Baths
    1.27
    Activations Density 0.026%

    No Known Activations