© 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. 12126
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to named entities—capitalized proper nouns such as place names, company or product names, section headers, etc.

    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
     ocurre
    0.89
     canales
    0.79
    齙
    0.79
     különb
    0.78
    ิ่น
    0.77
    PhysRev
    0.76
    CipherText
    0.76
     gobier
    0.75
    भाषित
    0.75
     ámbitos
    0.75
    POSITIVE LOGITS
    0.85
    it
    0.68
     red
    0.68
     pledge
    0.67
     rival
    0.66
     powder
    0.66
     secured
    0.66
    -
    0.66
     latest
    0.65
    Honestly
    0.65
    Activations Density 0.000%

    No Known Activations