© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3554
    Prev
    Next
    INDEX
    Explanations

    country names

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

    The neuron fires strongly on the “--(” token that marks the start of a press‐release dateline/newswire header.

    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
    o
    0.91
    e
    0.90
    ו
    0.89
    y
    0.82
    ي
    0.78
    u
    0.77
    s
    0.77
    f
    0.74
    g
    0.72
    i
    0.71
    POSITIVE LOGITS
     निकाले
    0.76
     ratus
    0.76
     assesses
    0.76
     esperan
    0.76
     consort
    0.75
     másik
    0.75
     intox
    0.75
     READER
    0.74
     Notiflix
    0.73
     தொடர்புடைய
    0.73
    Activations Density 0.003%

    No Known Activations