© 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. 10-GEMMASCOPE-RES-131K
    7. 100047
    Prev
    Next
    INDEX
    Explanations

    underserved disadvantaged populations

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

    words and phrases related to underserved, disadvantaged, or marginalized populations.

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

    The main thing this neuron does is detect mentions of economically or socially disadvantaged, underserved, or underrepresented populations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     colar
    -1.52
    inerario
    -1.46
     salas
    -1.41
     delas
    -1.40
     dangere
    -1.38
    余談
    -1.38
     arrend
    -1.34
     restos
    -1.34
     atitude
    -1.33
    étaro
    -1.32
    POSITIVE LOGITS
     of
    1.46
    这些
    1.46
     подоб
    1.44
    s
    1.41
     monochromatic
    1.35
    この
    1.30
    similar
    1.30
    ),
    1.30
    <b>
    1.29
    while
    1.29
    Activations Density 0.026%

    No Known Activations