© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9741
    Prev
    Next
    INDEX
    Explanations

    arrow, Torch, escape

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

    The neuron strongly signals the presence of proper‐noun tokens—especially product/brand names, domain names, and distinctive software or company 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
    n
    0.89
     stimuli
    0.88
    t
    0.80
    l
    0.76
    nte
    0.73
    lh
    0.71
    s
    0.71
    lj
    0.70
    lio
    0.69
     casualty
    0.69
    POSITIVE LOGITS
     encuent
    0.78
     государственной
    0.77
    abhavena
    0.77
    ğa
    0.77
     Estatal
    0.77
     YEAR
    0.75
    ilayer
    0.75
     incluyendo
    0.75
    languageTag
    0.75
     государство
    0.75
    Activations Density 0.000%

    No Known Activations