© 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. 13939
    Prev
    Next
    INDEX
    Explanations

    code syntax and punctuation

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

    This neuron detects the press‐release dateline marker “--(” that introduces the wire service code after a location.

    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
    督
    0.83
    av
    0.82
    ან
    0.80
    jaa
    0.79
    jiang
    0.78
    και
    0.77
    也
    0.77
    ische
    0.77
    ళ
    0.75
    Ratio
    0.74
    POSITIVE LOGITS
    liegen
    0.75
     romp
    0.74
     workflows
    0.74
     OCE
    0.73
    কর্মী
    0.73
     oiseaux
    0.73
     EVs
    0.73
    데요
    0.71
     EVO
    0.71
     Underwater
    0.71
    Activations Density 0.001%

    No Known Activations