© 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. 34-GEMMASCOPE-RES-131K
    7. 7072
    Prev
    Next
    INDEX
    Explanations

    landowners and communities

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

    This neuron fires on words naming local stakeholder groups or communities (e.g. farmers, protesters, residents, community).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Ordem
    -0.90
    ópolis
    -0.88
     Recu
    -0.87
    itete
    -0.86
    Clients
    -0.83
    żeli
    -0.82
    ү
    -0.82
    OMO
    -0.81
    pstmt
    -0.80
     pè
    -0.80
    POSITIVE LOGITS
     host
    1.86
     communities
    1.53
     Host
    1.45
    host
    1.40
    Host
    1.34
     hosting
    1.33
     landowners
    1.32
     hosts
    1.29
    communities
    1.16
    地元
    1.12
    Activations Density 0.024%

    No Known Activations