© 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. 34-GEMMASCOPE-RES-131K
    7. 103881
    Prev
    Next
    INDEX
    Explanations

    github.com links

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

    The neuron is highly activated by numeric tokens (e.g. years, version numbers, or other digit sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    voy
    -0.77
    dicos
    -0.73
    tric
    -0.72
     Tierney
    -0.71
     besonderes
    -0.69
    guess
    -0.68
    trial
    -0.68
    delay
    -0.66
    pricing
    -0.66
    mbio
    -0.66
    POSITIVE LOGITS
    顆
    0.71
     attaque
    0.69
     kdo
    0.69
    andis
    0.68
     Anforderungen
    0.68
     engineer
    0.66
     WAS
    0.65
    OTE
    0.65
     assail
    0.64
     Chung
    0.64
    Activations Density 0.072%

    No Known Activations