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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117701
    Prev
    Next
    INDEX
    Explanations

    granite and marble surfaces

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

    This neuron detects mentions of high-end stone surfaces—especially granite, marble, or travertine countertops and similar stone finishings.

    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
     marble
    -1.16
     granite
    -1.09
    Marble
    -0.90
     Marble
    -0.89
     Crunch
    -0.80
     sureties
    -0.80
     compartments
    -0.80
    uvre
    -0.79
    cepan
    -0.79
    Granite
    -0.78
    POSITIVE LOGITS
     tops
    0.91
     throughout
    0.81
     look
    0.80
     everywhere
    0.80
    😺
    0.78
    щением
    0.77
     and
    0.74
     top
    0.74
    씌
    0.72
     العلم
    0.70
    Activations Density 0.016%

    No Known Activations