© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14924
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on multi-syllable, content-rich nouns and proper noun compounds—especially uncommon or technical terms (e.g. “Monster Beverage Corporation,” “real-estate,” “tax-abusing,” “IPO”).

    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
     Hoboken
    0.76
     месе
    0.69
    ʼ
    0.68
     перемо
    0.66
    
    0.66
    URE
    0.66
    EndY
    0.64
    '=>'','
    0.63
     cancell
    0.62
     Nij
    0.62
    POSITIVE LOGITS
    िकर
    0.70
    खुद
    0.69
    ডেম
    0.68
    वुड
    0.66
    mgmt
    0.66
    iin
    0.66
    កម្ម
    0.64
     unfit
    0.64
    맟
    0.64
    oc
    0.63
    Activations Density 0.000%

    No Known Activations