© 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. 13327
    Prev
    Next
    INDEX
    Explanations

    types of people

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

    The neuron activates on words naming or describing groups of like-minded people or enthusiasts (e.g. “like-minded,” “dreamers,” “enthusiasts,” “lovers,” “thinkers”).

    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
     some
    -1.66
     time
    -1.38
     using
    -1.30
     key
    -1.30
     perbaikan
    -1.24
     cabang
    -1.23
     penggunaan
    -1.19
     essential
    -1.17
     areas
    -1.15
     alcune
    -1.15
    POSITIVE LOGITS
     who
    1.96
     [(
    1.41
     []:
    1.39
     ComVisible
    1.38
     MessageBoxIcon
    1.35
     textAlign
    1.33
    /***/
    1.31
    
    1.30
     الذين
    1.29
     représentent
    1.27
    Activations Density 0.107%

    No Known Activations