© 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. 68882
    Prev
    Next
    INDEX
    Explanations

    explanatory "as in"

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

    The neuron strongly activates on instances of the comparative phrase “as in” (i.e. the prepositions “as” and “in” when used together to introduce examples).

    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
    );
    -2.39
     on
    -2.14
    );
    -1.96
     in
    -1.94
    </td>
    -1.91
     for
    -1.84
    </th>
    -1.77
     всех
    -1.75
     In
    -1.69
     If
    -1.68
    POSITIVE LOGITS
     剧照
    2.16
    
    1.89
    “
    1.84
     合集
    1.79
     restoran
    1.78
     maksi
    1.77
    鮃
    1.75
    .“
    1.74
     eſſ
    1.74
    ,“
    1.73
    Activations Density 0.007%

    No Known Activations