© 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. 128945
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to numerical expressions (quantities, counts, and measurements) in technical or scientific text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    developments, value, pole, characteristic, structure, cure

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     limpeza
    -1.10
     nuoc
    -1.08
     NavController
    -1.03
     richied
    -1.02
    cision
    -1.00
     desblo
    -0.96
    を選び
    -0.96
    ⚣
    -0.96
     válvula
    -0.94
    Dort
    -0.94
    POSITIVE LOGITS
     for
    1.70
     when
    1.23
     also
    1.22
     in
    1.18
     of
    1.13
     остальных
    1.08
     інших
    0.94
     regarding
    0.94
     other
    0.92
     Her
    0.90
    Activations Density 0.106%

    No Known Activations