© 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. 5699
    Prev
    Next
    INDEX
    Explanations

    bullet points and lists

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

    The neuron fires on colon punctuation marks (":"), i.e., it detects list-introducing colons.

    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
     อ
    0.58
     Нужно
    0.57
     Frü
    0.55
     Поскольку
    0.54
     beiden
    0.54
     הח
    0.53
     Время
    0.53
     Қ
    0.52
     QText
    0.52
     ลักษณะ
    0.52
    POSITIVE LOGITS
    ↵↵
    0.83
    慧
    0.50
     commonplace
    0.48
    变得
    0.47
    된
    0.47
    成为
    0.46
    ↵↵↵
    0.45
     streamline
    0.45
     specialize
    0.45
    ↵↵↵↵↵
    0.45
    Activations Density 0.000%

    No Known Activations