© 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. 95663
    Prev
    Next
    INDEX
    Explanations

    circuit-switched data types

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

    This neuron activates on numeric and mathematical symbol tokens (digits, minus signs, dollar signs, etc.).

    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
     according
    -0.99
     According
    -0.98
     cordón
    -0.91
    érôme
    -0.88
    遗产
    -0.87
    Biochemical
    -0.85
     demonstrates
    -0.85
    ϑ
    -0.85
    According
    -0.84
     get
    -0.83
    POSITIVE LOGITS
    COORD
    1.13
     startling
    1.10
    لكن
    1.05
    animity
    1.05
    وقد
    1.04
    tailed
    1.04
     zelfs
    1.02
    Ꮒ
    1.02
     Bajos
    1.02
     absurd
    1.01
    Activations Density 0.009%

    No Known Activations