© 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. 15609
    Prev
    Next
    INDEX
    Explanations

    chess notation markers

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

    The neuron fires on rare, domain-specific or technical content words (high-information terms).

    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
    enças
    0.87
    ي
    0.79
    ্ৰ
    0.73
     Privilege
    0.70
    وى
    0.69
    во
    0.67
    блю
    0.67
     ભાગ
    0.67
    м
    0.67
    ೀರ್
    0.66
    POSITIVE LOGITS
    minute
    0.91
     hidrógeno
    0.89
    thai
    0.83
     dakika
    0.82
     života
    0.80
     appropriately
    0.79
    that
    0.79
    ming
    0.78
     міста
    0.78
     ऑर्
    0.78
    Activations Density 0.000%

    No Known Activations