© 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. 34-GEMMASCOPE-RES-131K
    7. 77301
    Prev
    Next
    INDEX
    Explanations

    names starting with Kes or Kas

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

    The neuron strongly activates on the character sequence “Kes,” picking out occurrences of that exact substring (e.g. in “Kesha,” “KESZ,” “Kessler,” 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_34/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
     either
    -0.94
     Schild
    -0.88
    iffy
    -0.81
     possible
    -0.79
     ブロック
    -0.79
     kostenlosen
    -0.79
     plegable
    -0.77
     Cister
    -0.75
    ͅ
    -0.75
     Possible
    -0.74
    POSITIVE LOGITS
     NOTICE
    0.82
    фон
    0.79
    ombres
    0.78
    NOTICE
    0.77
     ef
    0.75
    姫
    0.75
     Eduardo
    0.73
     Broome
    0.73
     Else
    0.73
     Ecology
    0.73
    Activations Density 0.012%

    No Known Activations