© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49514
    Prev
    Next
    INDEX
    Explanations

    stone, marble, granite

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

    This neuron fires on technical descriptions of stone surface treatments—especially mentions of applying heat to the surface of stone.

    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
     Sancho
    -0.88
     Illustrations
    -0.82
    木製
    -0.81
    Tin
    -0.80
     lowlands
    -0.80
    culares
    -0.78
     kovo
    -0.78
     Crespo
    -0.77
    Vaccine
    -0.77
    ╫
    -0.76
    POSITIVE LOGITS
     stone
    2.81
     marble
    2.77
     granite
    2.13
    marble
    2.09
     Marble
    2.02
     stones
    2.02
    石
    1.98
     Stone
    1.95
    Marble
    1.95
    stone
    1.80
    Activations Density 0.027%

    No Known Activations