© 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. 72927
    Prev
    Next
    INDEX
    Explanations

    proper noun identifiers

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

    The neuron activates specifically on the word “foundry” (including occurences in “Cloud Foundry”).

    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
    as
    -3.88
    .
    -3.50
     Other
    -3.08
    ”
    -2.95
    k
    -2.83
    w
    -2.81
    a
    -2.67
     During
    -2.66
    “
    -2.66
     “
    -2.55
    POSITIVE LOGITS
    渽
    3.06
    燹
    2.77
    瓛
    2.70
    ㈰
    2.67
    ࿙
    2.64
    RenderAtEndOf
    2.64
    
    2.63
    髎
    2.61
    }$.
    2.58
    faatkan
    2.58
    Activations Density 0.005%

    No Known Activations