© 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. 104693
    Prev
    Next
    INDEX
    Explanations

    traverse and traverse paths

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

    the word "traverse" or its variations (traversing, traversal).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The main thing this neuron does is detect occurrences of the verb “traverse” (and its variants) in text.

    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
    棡
    -2.41
    ㇼ
    -2.38
    enablog
    -2.30
    _
    -2.23
     важно
    -2.16
    </strong>
    -2.09
    歺
    -2.06
     podemos
    -2.05
    蛄
    -2.03
    
    -2.03
    POSITIVE LOGITS
    喾
    2.80
    ቍ
    2.75
    滹
    2.58
    尛
    2.56
    ㉕
    2.50
    
    2.50
    งิน
    2.48
     been
    2.48
     "../
    2.45
    噥
    2.45
    Activations Density 0.004%

    No Known Activations