© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67381
    Prev
    Next
    INDEX
    Explanations

    ├── YII├── framework├── flyweight├── pid├── pattern├── Go├── gatesidelib└── meter

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

    The neuron fires on software/library/framework names and other code‐module identifiers.

    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
    országban
    -1.55
    
    -1.48
    
    -1.43
     Semoga
    -1.40
    勿論
    -1.39
    vances
    -1.36
     condicion
    -1.36
     Bahkan
    -1.34
     docentes
    -1.33
     dokonce
    -1.32
    POSITIVE LOGITS
    .
    2.08
    1
    1.76
    \
    1.73
     was
    1.63
    The
    1.59
    '
    1.48
     again
    1.28
     with
    1.27
     wasn
    1.25
    由于
    1.25
    Activations Density 0.005%

    No Known Activations