© 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. 3778
    Prev
    Next
    INDEX
    Explanations

    toys

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

    The neuron detects mentions of “toy” or “toys” (and close variants) in the text.

    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
     \
    -3.19
    </sup>
    -3.09
    踅
    -2.52
    。”
    -2.45
    '
    -2.41
    </h6>
    -2.38
    鲣
    -2.31
    包围
    -2.22
    ...)
    -2.19
    )();
    -2.19
    POSITIVE LOGITS
    鉭
    2.70
    癭
    2.63
     刺繍
    2.63
    癀
    2.56
    翃
    2.52
    厹
    2.47
    ꜆
    2.45
    GillaGilla
    2.38
     บ้าน
    2.36
    ￬
    2.36
    Activations Density 0.004%

    No Known Activations