© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10761
    Prev
    Next
    INDEX
    Explanations

    son, youngest, daughter, father

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

    The neuron activates on past‐participle verbs ending in “-ed.”

    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
    I
    0.85
    ขอ
    0.77
    GTA
    0.75
    number
    0.74
    it
    0.73
     Insulin
    0.73
     I
    0.72
    ות
    0.72
    图片
    0.69
     Hast
    0.68
    POSITIVE LOGITS
     febbraio
    0.80
     hué
    0.79
     одежды
    0.78
     molde
    0.77
    ✙
    0.77
     జరిగ
    0.77
    ొప్పి
    0.75
     επίσης
    0.75
    PathParam
    0.73
     ensayo
    0.73
    Activations Density 0.000%

    No Known Activations