© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7420
    Prev
    Next
    INDEX
    Explanations

    program director

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

    The neuron consistently lights up on noun phrases naming concrete entities or topics (e.g. product names, organizational units, reports, folders, shows, analyzers).

    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
     and
    1.16
     மற்றும்
    0.97
    .
    0.88
     및
    0.86
     structures
    0.86
     systems
    0.84
     ਅਤੇ
    0.84
     which
    0.83
    /
    0.83
     и
    0.80
    POSITIVE LOGITS
    بعض
    0.98
    最初の
    0.85
    ယောက်
    0.84
     childish
    0.83
    自分の
    0.82
     sarcastic
    0.82
    簡単な
    0.79
     Taehyung
    0.78
     catchy
    0.77
     mischievous
    0.77
    Activations Density 0.000%

    No Known Activations