© 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. 31-GEMMASCOPE-2-RES-16K
    7. 916
    Prev
    Next
    INDEX
    Explanations

    It's Always Sunny in Philadelphia

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

    The neuron is primarily detecting personal pronouns (e.g. you, they, it) in subject position.

    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
    categorias
    0.53
    ாதார
    0.49
     convi
    0.49
     flew
    0.49
     contaba
    0.49
    昱
    0.49
     into
    0.49
    clientes
    0.48
    вій
    0.48
     categorize
    0.48
    POSITIVE LOGITS
     Very
    0.55
     উত্তম
    0.54
    Very
    0.52
     Restricted
    0.52
     Breeder
    0.51
     Greater
    0.50
     τὸ
    0.50
     talented
    0.50
    Ě
    0.50
    Laura
    0.50
    Activations Density 0.026%

    No Known Activations