© 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. 128252
    Prev
    Next
    INDEX
    Explanations

    Q: followed by colon

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

    The neuron activates on tokens naming external libraries, packages, or modules (e.g. in import/require paths).

    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
    蛱
    -1.76
    捋
    -1.75
    
    -1.74
    螅
    -1.73
     marcado
    -1.73
     condenado
    -1.72
     perdidos
    -1.67
    跸
    -1.67
     testigo
    -1.66
    鄕
    -1.65
    POSITIVE LOGITS
    0
    2.31
    7
    2.25
    6
    2.13
    9
    2.05
    5
    2.02
    8
    1.99
    y
    1.84
    /
    1.83
    2
    1.74
    3
    1.73
    Activations Density 0.005%

    No Known Activations