© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119001
    Prev
    Next
    INDEX
    Explanations

    matching

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

    The neuron detects occurrences of the word “match” (or its inflected form “matches”).

    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
    </em>
    -2.33
     $\
    -1.88
    ++];
    -1.88
    )$,
    -1.88
    )$
    -1.78
    ньому
    -1.73
    AFFIRMED
    -1.71
    ubscribe
    -1.68
    ):
    
    -1.67
    ());
    -1.66
    POSITIVE LOGITS
     the
    2.72
     your
    2.55
     législation
    1.88
     our
    1.86
     réglementation
    1.77
    おすすめの
    1.68
     behulp
    1.65
    了啊
    1.58
     principali
    1.56
     eficiente
    1.56
    Activations Density 0.021%

    No Known Activations