© 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. 5179
    Prev
    Next
    INDEX
    Explanations

    primes, sieve, list, append, Sci, between, daily, dose

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

    The neuron chiefly detects double-quote characters (") in the text.

    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
    ॰ऍ
    0.75
     kiosks
    0.74
     Nā
    0.74
     Ironically
    0.74
    ண
    0.73
     Beispiel
    0.73
     Deepika
    0.73
     éc
    0.72
     Deborah
    0.72
     Sita
    0.72
    POSITIVE LOGITS
    ultimo
    0.66
    ამდ
    0.64
    最強
    0.63
     verlieren
    0.62
    🇪
    0.61
    ตัวเอง
    0.61
    หลัง
    0.61
    ຕໍ່
    0.61
     вполне
    0.60
    اطع
    0.60
    Activations Density 0.004%

    No Known Activations