© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5165
    Prev
    Next
    INDEX
    Explanations

    told to, told that

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

    The neuron strongly activates on instances of reported speech or hearsay, especially the past‐passive “was told.”

    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
    во
    1.00
    t
    0.94
    ἀ
    0.90
    ru
    0.89
    ἆ
    0.89
    u
    0.88
    av
    0.87
     Phases
    0.86
    d
    0.86
     フ
    0.85
    POSITIVE LOGITS
    zelfde
    0.98
    Dto
    0.89
     erect
    0.86
     dormitorios
    0.83
     departamentos
    0.82
    ческих
    0.82
     sólo
    0.82
    可以是
    0.81
     شئ
    0.80
    byId
    0.80
    Activations Density 0.002%

    No Known Activations