© 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. 99738
    Prev
    Next
    INDEX
    Explanations

    bidirectional, direction, ways

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

    This neuron activates on words and phrases indicating directionality or movement flow (e.g., one-way, both ways, back-and-forth, bidirectional).

    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
     then
    -2.23
     {
    -1.52
     than
    -1.48
    
    -1.46
     =
    -1.36
     einzigen
    -1.35
    なども
    -1.34
    </b>
    -1.33
     einzige
    -1.32
     mismas
    -1.30
    POSITIVE LOGITS
     essayé
    1.57
     置物
    1.52
     peines
    1.50
     kateg
    1.48
     désol
    1.48
    液体
    1.48
    蕷
    1.45
     uppgifter
    1.45
     Entrega
    1.45
    􀂃
    1.45
    Activations Density 0.021%

    No Known Activations