© 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. 31-GEMMASCOPE-2-RES-16K
    7. 425
    Prev
    Next
    INDEX
    Explanations

    chat bot

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

    The neuron strongly responds to tokens beginning with the letters “Ch,” effectively detecting words or names that start with “Ch.”

    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
     meglio
    0.59
     entscheid
    0.57
     cuticle
    0.54
     Truly
    0.53
    HttpContext
    0.53
    쵝
    0.53
     Resonance
    0.52
     drawback
    0.52
     Pinnacle
    0.51
    MDEwOlJlcG
    0.50
    POSITIVE LOGITS
    Ch
    0.97
     Ch
    0.86
     Chom
    0.70
     Ч
    0.66
    등학교
    0.66
    isholm
    0.65
     チャ
    0.63
     Chats
    0.61
     CH
    0.60
     وچ
    0.60
    Activations Density 0.555%

    No Known Activations