© 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. 8421
    Prev
    Next
    INDEX
    Explanations

    mathematical or code symbols

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

    The neuron strongly activates on tokens that occur in academic‐style reference or citation listings (e.g. journal names, citation headers, etc.).

    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
    લ
    1.00
     bambini
    0.87
    ന്യൂ
    0.87
    ار
    0.85
    сти
    0.84
    гом
    0.83
    ле
    0.82
    letzt
    0.82
    ра
    0.82
    줬
    0.82
    POSITIVE LOGITS
     estuaries
    0.70
     Over
    0.68
     nuk
    0.68
     k
    0.67
     districts
    0.67
     independ
    0.66
     manufacturers
    0.66
    n
    0.65
     effluents
    0.65
     nucle
    0.64
    Activations Density 0.000%

    No Known Activations