© 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. 71675
    Prev
    Next
    INDEX
    Explanations

    listing items

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

    The neuron detects list-introducing terms such as “includes,” “including,” or their Chinese equivalent “包括.”

    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
    ↵↵
    -1.81
     hoffe
    -1.32
     löst
    -1.30
    lichung
    -1.30
     vote
    -1.30
    achting
    -1.27
     dün
    -1.27
    nią
    -1.24
     \
    -1.23
     tendremos
    -1.23
    POSITIVE LOGITS
     including
    2.08
     includes
    1.73
     include
    1.70
     to
    1.67
     also
    1.64
     is
    1.52
     också
    1.45
     säga
    1.45
     ۷
    1.42
     名前
    1.37
    Activations Density 0.066%

    No Known Activations