© 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. 34-GEMMASCOPE-RES-131K
    7. 93081
    Prev
    Next
    INDEX
    Explanations

    matchmaking

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

    The neuron is primarily detecting common English function words (e.g. articles, prepositions, and auxiliary verbs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Luc
    -0.78
    anj
    -0.75
    ückt
    -0.72
    даго
    -0.69
    thanx
    -0.69
    Ib
    -0.68
    DEX
    -0.68
    핑
    -0.68
    Located
    -0.68
     trabajos
    -0.66
    POSITIVE LOGITS
     matched
    2.03
     matches
    1.78
     match
    1.78
    matched
    1.68
     matching
    1.65
    Matched
    1.63
    matches
    1.62
     Matches
    1.59
    match
    1.56
    匹配
    1.53
    Activations Density 0.009%

    No Known Activations