© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58665
    Prev
    Next
    INDEX
    Explanations

    better serve people or things

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

    The neuron fires on occurrences of the verb “serve” (especially in phrases like “better serve”).

    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
     unending
    -1.85
     considerados
    -1.84
    噲
    -1.80
     ridiculously
    -1.77
     breathtaking
    -1.77
    
    -1.74
     dignidad
    -1.73
    ⮑
    -1.73
    𐄁
    -1.73
     acclaimed
    -1.72
    POSITIVE LOGITS
     because
    2.28
     will
    2.20
    0
    2.09
     three
    1.71
     when
    1.69
     can
    1.64
     with
    1.58
    s
    1.57
    6
    1.56
     came
    1.52
    Activations Density 0.030%

    No Known Activations