© 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. 65398
    Prev
    Next
    INDEX
    Explanations

    Loren Jones, presta valve

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

    This neuron responds to long, multi-syllabic, uncommon proper names or technical terms (e.g. foreign place names, scientific Latin names, and other specialized vocabulary).

    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
    AdvEx
    -3.11
    讦
    -2.98
    鲠
    -2.94
    颡
    -2.92
    ⢕
    -2.92
    咴
    -2.88
    䊉
    -2.84
    ዡ
    -2.84
    鲧
    -2.84
     باسلام
    -2.83
    POSITIVE LOGITS
    —
    3.89
    –
    3.67
    ...
    3.56
    <
    3.36
    The
    3.30
    --
    3.28
    -
    3.11
    ––
    3.00
    0
    2.91
    ",
    2.84
    Activations Density 0.872%

    No Known Activations