© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102673
    Prev
    Next
    INDEX
    Explanations

    names starting with Jas

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

    This neuron detects the character sequence “jas” within tokens (e.g. in Jasper, Jasmine, Jasmonic, Jasenovac).

    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
     حسین
    -0.78
    PRESSION
    -0.77
    elock
    -0.73
     metri
    -0.73
    law
    -0.73
    irected
    -0.72
     décid
    -0.72
    ществ
    -0.71
    getRandom
    -0.71
    rium
    -0.71
    POSITIVE LOGITS
     Jasper
    0.97
     Jas
    0.91
    Jasper
    0.91
     complies
    0.81
    世話
    0.79
     Landkreis
    0.76
    Compiled
    0.75
    pushd
    0.75
     Engines
    0.75
    inactive
    0.74
    Activations Density 0.007%

    No Known Activations