© 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. 9406
    Prev
    Next
    INDEX
    Explanations

    python `__init__` method

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

    The neuron is keyed to bibliographic metadata tokens—particularly numeric citation data (e.g. years, volume/issue numbers) in scholarly references.

    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
     mengh
    0.82
    祂
    0.82
    entend
    0.81
     توسط
    0.79
    />}/>
    0.79
     محد
    0.78
     αργ
    0.78
    oré
    0.78
    形势
    0.77
     orthogon
    0.75
    POSITIVE LOGITS
    y
    0.86
    이지
    0.74
     day
    0.73
    АР
    0.72
     ਡ
    0.71
     \
    0.70
     Was
    0.70
    yiz
    0.70
     fortified
    0.68
     proprietor
    0.67
    Activations Density 0.001%

    No Known Activations