© 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. 22-GEMMASCOPE-RES-131K
    7. 40095
    Prev
    Next
    INDEX
    Explanations

    code strings or variables

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

    This neuron fires on numeric literals (numbers) in the 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
     keď
    -0.99
     other
    -0.93
     in
    -0.93
     instead
    -0.89
     andere
    -0.88
     innych
    -0.88
    brille
    -0.88
     if
    -0.87
    无数
    -0.87
     with
    -0.86
    POSITIVE LOGITS
    Πηγές
    0.90
     strictement
    0.88
     Mirza
    0.86
     kazak
    0.86
    yesha
    0.86
     herbes
    0.85
     dosa
    0.85
     exal
    0.84
    cuál
    0.82
    зраст
    0.82
    Activations Density 0.010%

    No Known Activations