© 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. 22-GEMMASCOPE-RES-131K
    4. 12792
    Prev
    Next
    INDEX
    Explanations

    population data

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

    census population data in articles about towns and localities.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects numeric tokens—i.e. any standalone numbers or digit sequences in the text.

    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
    清
    -1.06
    向了
    -1.00
    安静
    -1.00
    和
    -1.00
    出発
    -1.00
    就开始
    -0.98
     zeven
    -0.98
    高
    -0.97
     Treffen
    -0.96
     dizaine
    -0.96
    POSITIVE LOGITS
    plings
    1.28
     recent
    1.01
    
    1.00
    stützung
    0.99
    缺点
    0.98
    机器人
    0.98
    complished
    0.98
     RBIs
    0.98
     casais
    0.97
    瞬
    0.96
    Activations Density 0.047%

    No Known Activations