© 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. 10-GEMMASCOPE-RES-131K
    7. 61289
    Prev
    Next
    INDEX
    Explanations

    stone, granite, marble, brick, tile

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

    The neuron strongly activates on mentions of construction or finish materials (stone, wood, granite, steel, marble, tile, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    \
    -1.59
     
    -1.43
    henswürdigkeiten
    -1.43
     pérd
    -1.41
     castig
    -1.36
    anym
    -1.36
    にゃ
    -1.36
    (
    -1.36
    =
    -1.35
     memorandum
    -1.34
    POSITIVE LOGITS
     With
    2.16
    ！"
    1.97
     dengan
    1.88
     ที่
    1.81
     or
    1.74
    Through
    1.70
    Both
    1.70
     That
    1.70
    Because
    1.69
     through
    1.68
    Activations Density 0.017%

    No Known Activations