© 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. 3253
    Prev
    Next
    INDEX
    Explanations

    HOME to 741741

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

    The neuron is selectively detecting personal names (proper‐name tokens, especially surnames) in the text.

    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
    ="">
    0.57
     alten
    0.57
     Siamese
    0.54
     neoplastic
    0.52
     {
    0.52
    0.52
     Madagascar
    0.51
     ❤
    0.51
     unnatural
    0.51
     antigo
    0.51
    POSITIVE LOGITS
    anwhile
    0.67
     afirmou
    0.64
     gave
    0.63
    on
    0.63
     afirmó
    0.63
    認為
    0.61
     অবশ্য
    0.61
     tomó
    0.60
     took
    0.60
    hofer
    0.60
    Activations Density 0.000%

    No Known Activations