© 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. 8415
    Prev
    Next
    INDEX
    Explanations

    This neuron detects the token “to” when it appears as the middle part of a hyphenated compound (e.g. “made-to-order”).

    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
    isEmpty
    0.45
    ;
    0.43
    java
    0.41
    Clazz
    0.41
    begin
    0.40
    、
    0.40
    typeface
    0.39
    container
    0.38
    champion
    0.38
    handleSubmit
    0.38
    POSITIVE LOGITS
     Ayurvedic
    0.48
    尽量
    0.46
     PFAS
    0.45
     repeatability
    0.44
     باستخدام
    0.44
     навіть
    0.44
     российских
    0.44
     특정
    0.44
     mitophagy
    0.43
     耐
    0.42
    Activations Density 0.000%

    No Known Activations