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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9980
    Prev
    Next
    INDEX
    Explanations

    writing limitations

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

    This neuron detects conditional clauses—phrases that set terms or requirements (e.g. “as long as,” “once,” “if,” etc.).

    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
    不得不
    0.64
    >′
    0.62
    被迫
    0.59
    没办法
    0.59
    ㅠㅠ
    0.57
     :(
    0.56
    😫
    0.56
    ㅠ
    0.55
    😢
    0.54
    😩
    0.54
    POSITIVE LOGITS
    只要
    2.67
     Provided
    1.74
     provided
    1.72
    provided
    1.67
     PROVIDED
    1.62
    Provided
    1.55
    只需要
    1.35
    只需
    1.31
     sofern
    1.28
     যতক্ষণ
    1.25
    Activations Density 0.390%

    No Known Activations