© 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. 22-GEMMASCOPE-RES-131K
    7. 26016
    Prev
    Next
    INDEX
    Explanations

    Q: and INDIA AT

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

    The neuron fires on numeric literals (integer constants) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Here
    -1.04
    guei
    -1.01
     to
    -0.97
    They
    -0.95
     蓝
    -0.92
     isoli
    -0.87
     登録
    -0.86
     generated
    -0.85
    сятся
    -0.85
    /*++
    -0.85
    POSITIVE LOGITS
     out
    0.96
     ocho
    0.93
     weißem
    0.92
    级的
    0.85
     fon
    0.84
     Prosecution
    0.84
     soldado
    0.84
    ätzen
    0.84
    红的
    0.83
     папа
    0.82
    Activations Density 0.008%

    No Known Activations