© 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. 44
    Prev
    Next
    INDEX
    Explanations

    population and geographic areas

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

    statistical information in geographical articles, particularly population data.

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

    The neuron flags passages reporting numeric demographic or administrative statistics (e.g. census counts, population figures, areas).

    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
    abstractmethod
    -0.94
    उत्तर
    -0.94
    groet
    -0.93
    věd
    -0.92
    aarrggbb
    -0.91
     recompensa
    -0.90
     góry
    -0.88
     policía
    -0.88
     Privacidade
    -0.88
    Literat
    -0.88
    POSITIVE LOGITS
     and
    0.88
    Ff
    0.84
     compared
    0.84
     BIB
    0.81
    oup
    0.80
    ACHE
    0.79
     Однако
    0.79
    h
    0.77
    echa
    0.77
    кспер
    0.77
    Activations Density 0.052%

    No Known Activations