© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75901
    Prev
    Next
    INDEX
    Explanations

    computer science and networking terms

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

    The neuron is specialized in detecting standalone numeric tokens (numbers and version identifiers).

    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
    šiť
    -0.81
    🧰
    -0.81
    vskip
    -0.80
     mimpi
    -0.77
    "><?
    -0.75
    inigungs
    -0.75
    Кан
    -0.74
     comedians
    -0.74
    дневно
    -0.74
    iqué
    -0.73
    POSITIVE LOGITS
     host
    1.01
     hosts
    0.93
    host
    0.88
     Host
    0.87
     Royal
    0.85
     Royale
    0.83
    Host
    0.82
    bell
    0.81
     Riverside
    0.79
    OutputPath
    0.79
    Activations Density 0.003%

    No Known Activations