© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102584
    Prev
    Next
    INDEX
    Explanations

    asking to determine something

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

    This neuron detects the imperative prompt “Determine” (i.e. when a question or instruction begins with the word “Determine”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    y
    -3.83
     '
    -3.48
    的
    -3.13
     queste
    -3.08
     boneka
    -2.98
    떳
    -2.89
    」，
    -2.84
    derdag
    -2.83
     pembun
    -2.83
    𖣘
    -2.81
    POSITIVE LOGITS
    珢
    3.42
    韪
    3.08
    浥
    2.91
    玧
    2.81
    嫘
    2.78
    焌
    2.78
    齷
    2.72
    嵎
    2.72
    锜
    2.66
    趼
    2.64
    Activations Density 0.031%

    No Known Activations