© 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. 12682
    Prev
    Next
    INDEX
    Explanations

    question about what follows

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

    The neuron selectively lights up on named entities—especially organization and place names.

    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
    overs
    0.59
     માત્ર
    0.56
     მხოლოდ
    0.56
    兕
    0.56
     ته
    0.53
    enhuma
    0.53
    蔑
    0.53
    iria
    0.52
    ょ
    0.52
     simplement
    0.51
    POSITIVE LOGITS
    真正
    0.65
     dessa
    0.63
     detta
    0.62
     proponent
    0.62
     най
    0.62
     проблемой
    0.62
    सबसे
    0.59
     entscheiden
    0.59
     Dessa
    0.59
    ้ำ
    0.59
    Activations Density 0.115%

    No Known Activations