© 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. 4208
    Prev
    Next
    INDEX
    Explanations

    granite countertops

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

    The main thing this neuron does is detect mentions of granite surfaces—especially granite countertops or slab-granite kitchen islands.

    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
    ),),
    -0.82
    ujian
    -0.77
     tariff
    -0.72
    ובר
    -0.69
    ynes
    -0.69
    规
    -0.69
    tissa
    -0.69
    >>,
    -0.68
    root
    -0.67
     Dunk
    -0.67
    POSITIVE LOGITS
     granite
    2.23
     quartz
    2.03
     countertops
    1.81
     Granite
    1.76
     Quartz
    1.67
     stone
    1.66
    Granite
    1.59
    quartz
    1.55
    Quartz
    1.54
     countertop
    1.42
    Activations Density 0.014%

    No Known Activations