© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65988
    Prev
    Next
    INDEX
    Explanations

    open the door for, options

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

    This neuron detects occurrences of “open” (and its inflected forms like “opens,” “leaves … open,” or “opens the door for”) indicating availability or opportunity.

    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
     že
    -1.58
    </td>
    -1.52
    ऎ
    -1.52
     bricola
    -1.52
     cheminée
    -1.48
    すでに
    -1.46
    彇
    -1.46
     Chinois
    -1.46
     venter
    -1.44
     goud
    -1.43
    POSITIVE LOGITS
     possibility
    2.28
     opportunity
    1.94
     first
    1.75
     chance
    1.71
    ing
    1.62
     question
    1.59
     option
    1.51
     YOU
    1.51
    Zubereitung
    1.50
     advantage
    1.48
    Activations Density 0.028%

    No Known Activations