© 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. 15719
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on named entities and headline-style proper nouns (e.g. place names, brand or product names, company names, 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
     proteínas
    0.95
     regiões
    0.89
     antaranya
    0.88
    Puedes
    0.87
    ။
    0.87
    ۔
    0.86
    ými
    0.85
     ideias
    0.85
    jähr
    0.84
    łoży
    0.84
    POSITIVE LOGITS
    s
    0.91
     是
    0.89
    是
    0.80
     is
    0.79
     =
    0.79
    pose
    0.78
    rt
    0.77
     Lieutenant
    0.77
     A
    0.75
    les
    0.75
    Activations Density 17.381%

    No Known Activations