© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72712
    Prev
    Next
    INDEX
    Explanations

    Nationwide population study

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

    This neuron identifies nationwide or population-based research studies, particularly activating on phrases like "population-based study," "nationwide database," and statistical data references.

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

    The neuron activates on numeric and quantitative data (counts, percentages, years, measurements).

    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
     others
    -1.27
     áreas
    -1.11
     other
    -1.11
    ösung
    -1.10
     when
    -1.06
     otros
    -1.05
     фрук
    -1.05
    了下去
    -1.04
     área
    -1.02
     that
    -1.01
    POSITIVE LOGITS
     worldwide
    1.43
    Between
    1.23
    From
    1.10
     suffisamment
    1.08
    Which
    1.08
    mejores
    1.06
     recent
    1.02
    顔が
    1.02
    complished
    1.02
     ботинки
    1.02
    Activations Density 0.229%

    No Known Activations