© 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. 8783
    Prev
    Next
    INDEX
    Explanations

    including

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

    The neuron strongly responds to content‐bearing nouns—especially plural/common nouns (e.g. “adventures,” “things,” “improvements,” “functions”).

    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
    它的
    0.83
     it
    0.80
    มัน
    0.74
     its
    0.70
     twice
    0.68
     obligatoire
    0.68
    ≣
    0.68
     flaw
    0.67
    ర్‌
    0.67
    它
    0.66
    POSITIVE LOGITS
     including
    2.20
    包括
    2.17
    including
    2.06
     incluyendo
    1.98
    比如
    1.93
     包括
    1.91
     Including
    1.88
     включая
    1.87
     incluindo
    1.85
     antaranya
    1.83
    Activations Density 1.088%

    No Known Activations