© 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. 99050
    Prev
    Next
    INDEX
    Explanations

    names starting with Kas

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

    The neuron activates on tokens containing the letter sequence “Kas,” i.e. proper names or terms that include “Kas.”

    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
    жі
    -0.82
    bezpe
    -0.81
     partly
    -0.80
    creat
    -0.80
     extraordinary
    -0.75
     nhiêu
    -0.75
     phenomenal
    -0.74
    ongono
    -0.73
     口コミ
    -0.72
    daos
    -0.71
    POSITIVE LOGITS
     Kas
    0.93
    Kas
    0.89
     новый
    0.87
    реса
    0.86
     KAS
    0.82
     CONF
    0.79
     Gifford
    0.78
     UPDATE
    0.77
    ILayout
    0.75
     resuming
    0.75
    Activations Density 0.012%

    No Known Activations