© 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. 128306
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numeric literals (numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    declaration of parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    pozorn
    -0.87
    rimos
    -0.86
     《
    -0.86
    แล้ว
    -0.85
     Drž
    -0.84
     ofreci
    -0.83
     NAV
    -0.82
    、「
    -0.81
     Behörden
    -0.81
     اهداف
    -0.81
    POSITIVE LOGITS
     ίδ
    0.93
    💛
    0.92
    ♥️
    0.92
     angelo
    0.90
     osserva
    0.88
     culturali
    0.88
     interieur
    0.88
    댈
    0.87
     столь
    0.85
     trovo
    0.84
    Activations Density 0.009%

    No Known Activations