© 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. 16228
    Prev
    Next
    INDEX
    Explanations

    Calculations with specific words

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

    The neuron is picking out forum/Q&A metadata and metrics—things like “Replied,” “Answered,” timestamps or dates, counts, and similar numeric/response markers in posts.

    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
     elección
    0.83
    G
    0.79
    T
    0.77
     एग्जाम्स
    0.74
    codec
    0.73
    C
    0.73
    ె
    0.73
    ar
    0.72
    せない
    0.72
    міна
    0.71
    POSITIVE LOGITS
     받았
    0.75
    biggr
    0.68
    률
    0.67
    檛
    0.64
     hastened
    0.64
     Nug
    0.63
     geeft
    0.62
     summand
    0.62
     분류
    0.61
     floc
    0.61
    Activations Density 0.000%

    No Known Activations