© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75281
    Prev
    Next
    INDEX
    Explanations

    connected to something

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

    This neuron fires on tokens containing the root “connect,” such as connected or disconnected.

    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
    e
    -2.97
    わから
    -2.83
    蕷
    -2.55
    </i>
    -2.39
     progrès
    -2.27
    hamilan
    -2.22
    琹
    -2.22
    わからない
    -2.22
    ING
    -2.19
    籥
    -2.19
    POSITIVE LOGITS
    後期
    3.11
     That
    2.97
    ness
    2.81
    ،
    2.75
    衪
    2.66
     emphasizes
    2.45
     pushes
    2.41
     Each
    2.34
    ']
    2.34
     Essentially
    2.30
    Activations Density 0.008%

    No Known Activations