© 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. 41058
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

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

    This neuron fires on tokens containing the character sequence “ken” (e.g. names like Kendrick and Kendra, the word Kendo, 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
    衚
    -2.97
    偌
    -2.67
     a
    -2.64
    兕
    -2.59
     مدير
    -2.48
    ."
    -2.48
    多谢
    -2.47
    
    -2.42
    </i>
    -2.30
     Konferenz
    -2.27
    POSITIVE LOGITS
    the
    3.13
    或
    2.81
    他的
    2.61
    ”、“
    2.52
    We
    2.38
    ”（
    2.36
    ”？
    2.34
    ();
    2.28
     הם
    2.28
    你可以
    2.27
    Activations Density 0.005%

    No Known Activations