© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6208
    Prev
    Next
    INDEX
    Explanations

    main street

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

    The neuron responds strongly to unusually long (multi-syllable or multi-part) words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     говорить
    0.86
    apiUrl
    0.81
     शेयरों
    0.80
    율
    0.79
     Consultado
    0.77
    styled
    0.76
    उन्होंने
    0.75
    Styled
    0.75
    論文
    0.75
    걔
    0.75
    POSITIVE LOGITS
    י
    0.87
     possibles
    0.80
     mén
    0.75
    ي
    0.75
     détect
    0.74
     Në
    0.73
     quaerat
    0.73
     possible
    0.72
     nanoscale
    0.72
    ningarna
    0.71
    Activations Density 0.001%

    No Known Activations