© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13478
    Prev
    Next
    INDEX
    Explanations

    Names with 'a'/'l'/'i'/'o' sounds

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

    This neuron consistently activates on occurrences of the proper name “Carl” (and its extensions such as “Carlin” or “Carlstad”), i.e. mentions of that specific person’s name.

    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_31_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
    ்ட
    0.59
    ليس
    0.58
    ardin
    0.54
     Koles
    0.54
    ürü
    0.54
    ("{}
    0.54
     Người
    0.53
     Arsen
    0.52
    мії
    0.52
    र्पण
    0.52
    POSITIVE LOGITS
    ifornia
    0.63
    otta
    0.59
    یداری
    0.57
     দলকে
    0.57
    sruhe
    0.57
    ottesville
    0.56
    setBorder
    0.56
    ിക്കു
    0.55
    Transform
    0.54
    Permalink
    0.54
    Activations Density 0.390%

    No Known Activations