© 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. 47799
    Prev
    Next
    INDEX
    Explanations

    passenger vehicles

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find mentions of “passenger” (e.g. in “passenger car,” “passenger side,” etc.).

    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
    y
    -3.27
    ?"
    -2.50
     was
    -2.41
    幛
    -2.38
    埽
    -2.27
    」
    -2.25
    ⢊
    -2.23
     unſ
    -2.22
    </strong>
    -2.20
    quê
    -2.20
    POSITIVE LOGITS
    ご馳走
    2.53
     After
    2.45
    する
    2.36
    嵎
    2.31
    久し
    2.22
    
    2.20
    ization
    2.20
    いろんな
    2.19
     ausführ
    2.19
     tatsäch
    2.16
    Activations Density 0.002%

    No Known Activations