© 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. 82686
    Prev
    Next
    INDEX
    Explanations

    capacity building

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

    The neuron is looking for mentions of “capacity building” or related capacity-building initiatives.

    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
    ച
    -0.72
    게
    -0.68
    anneau
    -0.68
    >)</
    -0.67
     posky
    -0.67
    muffin
    -0.66
    ̡
    -0.66
     новым
    -0.65
    Provide
    -0.65
    Provides
    -0.65
    POSITIVE LOGITS
     build
    5.59
     building
    5.25
    build
    4.72
     builds
    4.59
    building
    4.38
     Build
    4.16
    Build
    4.13
    Building
    4.03
     Building
    3.97
     buildup
    3.83
    Activations Density 0.101%

    No Known Activations