© 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. 41981
    Prev
    Next
    INDEX
    Explanations

    how to write code

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

    The neuron fires on Chinese question words—especially the interrogative pronoun “什么.”

    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
    垆
    -2.55
    踯
    -2.55
    퐼
    -2.53
    廔
    -2.44
    
    -2.42
    襌
    -2.42
     hemd
    -2.39
    ﹍﹍
    -2.36
     ferti
    -2.33
     ert
    -2.33
    POSITIVE LOGITS
    '
    2.55
    }
    2.50
    ↵↵
    2.48
    .
    2.47
     -
    2.08
    </h4>
    2.03
    </h3>
    2.03
     (
    2.02
     I
    1.93
    ходят
    1.93
    Activations Density 0.001%

    No Known Activations