© 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. 1032
    Prev
    Next
    INDEX
    Explanations

    kept secret until

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

    This neuron detects passages that specify a person’s address or current residence (e.g., “resides in …,” “giving her address as …,” “voter ID number is …”).

    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
     ホイールセット
    0.72
    ików
    0.66
     oraș
    0.64
    콰
    0.64
    trashButton
    0.63
     туристи
    0.63
    шо
    0.61
    recyclerview
    0.61
    восто
    0.60
     fraîche
    0.60
    POSITIVE LOGITS
    揩
    0.70
     demur
    0.67
     sixty
    0.65
     Carney
    0.65
     thirty
    0.64
     appellee
    0.63
     felony
    0.63
     allegation
    0.63
     willfully
    0.63
     lien
    0.63
    Activations Density 0.003%

    No Known Activations