© 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. 66093
    Prev
    Next
    INDEX
    Explanations

    playing cards

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

    This neuron fires on any token containing the substring “spa” (e.g. Spa de, Spa tha, spat, 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
    彀
    -2.77
    桕
    -2.75
    祤
    -2.69
    餿
    -2.61
    )’
    -2.45
    ཫ
    -2.42
    に於
    -2.38
    蠵
    -2.36
    鰾
    -2.33
    ”?
    -2.31
    POSITIVE LOGITS
    )
    2.97
    \\
    2.61
    2
    2.58
    --
    2.52
    ',
    2.48
    ６
    2.47
    If
    2.45
    and
    2.45
    或者
    2.42
    ."
    2.38
    Activations Density 0.002%

    No Known Activations