© 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. 15191
    Prev
    Next
    INDEX
    Explanations

    people and their demographic groups

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

    The neuron activates on words that name or describe demographic groups (e.g. ethnicities, nationalities, or other population categories).

    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
     ognuno
    -1.16
    更何况
    -1.13
    総評
    -1.08
    Fiat
    -1.08
     quelqu
    -1.08
    𝜏
    -1.04
    何况
    -1.02
    INGREDIENT
    -1.02
    Periods
    -1.02
     répond
    -1.02
    POSITIVE LOGITS
     children
    1.53
     family
    1.48
     girl
    1.43
     young
    1.41
     families
    1.40
     female
    1.35
     parents
    1.26
     kids
    1.25
     women
    1.24
     youth
    1.21
    Activations Density 0.082%

    No Known Activations