© 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. 67364
    Prev
    Next
    INDEX
    Explanations

    jig, jigsaw, assemblage

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

    The neuron fires on occurrences of the character sequence “jig” (e.g. jig, jigs, jigger, jigsaw).

    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
    ⩥
    -3.27
    
    -3.16
     撮っ
    -2.95
    ༷
    -2.81
    縯
    -2.66
    を購入
    -2.56
    椟
    -2.53
    昞
    -2.50
    鰱
    -2.50
    曏
    -2.50
    POSITIVE LOGITS
    '
    4.19
    ’
    2.91
     
    2.56
     "
    2.47
    ,"
    2.42
    All
    2.39
    知道
    2.36
    u
    2.33
    if
    2.25
    section
    2.22
    Activations Density 0.001%

    No Known Activations