© 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. 14698
    Prev
    Next
    INDEX
    Explanations

    kes, Kesha, Stokes

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

    The neuron fires on any token containing the letter sequence “kes” (e.g. Stokes, Sykes, Kesha).

    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
    ↵
    -2.84
    v
    -2.72
      
    -2.64
    In
    -2.50
    k
    -2.44
    ations
    -2.42
    ↵↵
    -2.41
    this
    -2.36
    Y
    -2.33
    ”
    -2.33
    POSITIVE LOGITS
    archiwizowane
    3.11
    癶
    2.61
    ſu
    2.56
    詎
    2.50
    鵟
    2.48
    änemark
    2.47
    kes
    2.47
    ي
    2.39
     Produkten
    2.38
    瘰
    2.36
    Activations Density 0.009%

    No Known Activations