© 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. 5534
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on list‐style enumerations (items or numbers separated by commas or other list markers).

    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
     Tast
    0.75
    mila
    0.74
    '
    0.73
    מא
    0.69
     juste
    0.68
    lo
    0.65
    pport
    0.63
    బె
    0.63
    о
    0.63
    нь
    0.63
    POSITIVE LOGITS
     ferrite
    0.97
     inkjet
    0.95
     fermion
    0.92
     violin
    0.91
     jellyfish
    0.90
     infrared
    0.90
     dimmer
    0.90
     vudd
    0.89
     piezo
    0.89
     fluorescent
    0.88
    Activations Density 0.000%

    No Known Activations