© 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. 2139
    Prev
    Next
    INDEX
    Explanations

    quotations or specific terms

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

    This neuron activates on proper nouns and other named entities (e.g. brand names, product names, organization or place names, and similar capitalized 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
    !</
    0.79
    ﺎ
    0.77
    💍
    0.76
    АТ
    0.74
     lớ
    0.73
    та
    0.73
    ть
    0.73
    גיע
    0.73
    ahkan
    0.71
     đau
    0.71
    POSITIVE LOGITS
     sogenannte
    1.05
     sogenannten
    1.04
     National
    0.99
     cosidd
    0.98
    jenigen
    0.84
     wichtigsten
    0.82
     American
    0.81
     S
    0.80
     jeweiligen
    0.80
     M
    0.79
    Activations Density 0.204%

    No Known Activations