© 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. 129830
    Prev
    Next
    INDEX
    Explanations

    carnitine and carnival

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

    The neuron fires on tokens containing the substring “carni,” such as in “carnival” or “carnitine.”

    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
    
    -2.75
    
    -2.48
    岨
    -2.44
     \_
    -2.36
    
    -2.33
    ﮦ
    -2.23
     trabal
    -2.22
     suporte
    -2.17
    referred
    -2.14
    发生了
    -2.11
    POSITIVE LOGITS
    ↵↵
    2.92
    a
    2.55
    e
    2.28
    .
    2.05
    ;
    2.03
    }(
    2.02
     That
    1.96
     These
    1.94
    <i>
    1.91
    nten
    1.88
    Activations Density 0.005%

    No Known Activations