© 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. 10960
    Prev
    Next
    INDEX
    Explanations

    body parts and related pain/discomfort

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

    The neuron detects mentions of specific game‐time markers and temporal segments in sports reporting (e.g. “injury time,” “half-time,” “late in the third period,” etc.).

    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
     அனைவரும்
    0.83
     majest
    0.69
     মাননীয়
    0.68
     imprescindible
    0.68
    綺麗な
    0.68
     wundersch
    0.66
     невероят
    0.64
    においては
    0.63
     majestic
    0.63
     NONE
    0.63
    POSITIVE LOGITS
    ​.
    0.76
    และ
    0.67
     하지만
    0.67
    .​​
    0.67
     ਅਤੇ
    0.64
     және
    0.64
    .​
    0.64
    和其他
    0.64
     apiece
    0.64
     zařízení
    0.64
    Activations Density 0.023%

    No Known Activations