© 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. 4722
    Prev
    Next
    INDEX
    Explanations

    cryptography, UV Index, debt ceiling

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

    This neuron detects news‐style byline and dateline markers (e.g. “By,” all‐caps city abbreviations, “Mr.”) at the start of articles.

    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
    -
    0.98
    ’
    0.86
    M
    0.69
    /
    0.65
    F
    0.62
    S
    0.61
    '
    0.61
    G
    0.60
    ian
    0.59
    E
    0.59
    POSITIVE LOGITS
     प्रत्येक
    0.71
    lblCredits
    0.63
     Fleurit
    0.61
    🥡
    0.60
     LOTRAchievement
    0.60
    ጨም
    0.60
    বিভিন্ন
    0.60
    cpuCycle
    0.59
    अन्य
    0.59
    किसी
    0.58
    Activations Density 0.000%

    No Known Activations