© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9294
    Prev
    Next
    INDEX
    Explanations

    names or name

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on words that denote naming or labels (e.g. name, named, rename) and on specific proper‐name tokens (addresses, file names, brand or entity names).

    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
     Höhe
    0.86
    해서
    0.84
     sentado
    0.84
    ص
    0.82
     estime
    0.80
    인트
    0.80
    supp
    0.79
    みて
    0.78
     esperando
    0.77
    挟
    0.77
    POSITIVE LOGITS
     name
    2.34
     names
    2.27
     Names
    2.02
    name
    1.96
     имена
    1.87
     Name
    1.82
    名字
    1.82
     NAME
    1.70
     getName
    1.68
    Names
    1.66
    Activations Density 2.023%

    No Known Activations