© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43595
    Prev
    Next
    INDEX
    Explanations

    hospitals and associations

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

    The neuron specifically fires on the names of formal institutions or organizations (e.g. hospitals, universities, associations, government agencies).

    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
    itudinal
    -1.45
     cioc
    -1.44
     alcool
    -1.38
     bourg
    -1.37
     linge
    -1.36
     masina
    -1.33
    fications
    -1.30
     solida
    -1.30
    umerable
    -1.28
     ditt
    -1.28
    POSITIVE LOGITS
     of
    2.34
     sogar
    1.68
     your
    1.45
     trám
    1.45
    最后由
    1.43
     BECAUSE
    1.41
     refiri
    1.38
     chamado
    1.34
     suficientemente
    1.34
    .‏
    1.32
    Activations Density 0.222%

    No Known Activations