© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1935
    Prev
    Next
    INDEX
    Explanations

    names, often followed by a last name

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

    The neuron strongly activates on tokens that are people’s proper 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
    Что
    0.45
    При
    0.45
    Для
    0.44
    ("");
    0.42
    ávy
    0.41
    DialogWhen
    0.40
    abilità
    0.40
    MeOH
    0.40
    CGPoint
    0.40
    Очень
    0.40
    POSITIVE LOGITS
     Lee
    0.60
     Wood
    0.57
     Martin
    0.57
     R
    0.56
     J
    0.56
     L
    0.54
     Williams
    0.53
     Miller
    0.52
     Clark
    0.52
     Johnson
    0.51
    Activations Density 0.076%

    No Known Activations