© 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. 4370
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on proper names and other rare, specialized terms (i.e. named entities).

    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
    িট
    0.76
    awks
    0.70
    ্যেষ্ঠ
    0.69
    essive
    0.68
    ੍ਹ
    0.67
    Stderr
    0.67
    ायचे
    0.66
    އ
    0.66
    culoskeletal
    0.64
    odesmium
    0.64
    POSITIVE LOGITS
     muda
    0.80
     encontraron
    0.78
     fascist
    0.76
     ejerc
    0.75
    ri
    0.74
     unfounded
    0.74
     bastion
    0.73
     financiers
    0.73
     despot
    0.73
     puedan
    0.72
    Activations Density 0.003%

    No Known Activations