© 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. 26423
    Prev
    Next
    INDEX
    Explanations

    either/or choices or administrations

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

    This neuron activates on numeric measurements and dosage values (e.g. concentrations, time points, weights) in scientific/medical text.

    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
     you
    -1.14
     конечно
    -1.06
     is
    -1.06
    0
    -1.05
     هو
    -1.05
     these
    -1.04
     utilizza
    -0.96
    这些
    -0.96
     philippe
    -0.95
    之间
    -0.94
    POSITIVE LOGITS
     either
    1.57
    either
    1.33
     from
    1.24
     or
    1.22
     at
    1.10
    oneof
    1.09
     soin
    1.08
    谕
    1.08
     Francus
    1.06
    Either
    1.05
    Activations Density 0.309%

    No Known Activations