© 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. 34-GEMMASCOPE-RES-131K
    7. 57203
    Prev
    Next
    INDEX
    Explanations

    locations of institutions

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

    The neuron detects institutional affiliation blocks by picking up department and university names (and their related location tokens).

    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
     which
    -1.27
     this
    -1.14
     about
    -1.08
     if
    -1.07
     at
    -1.04
     because
    -1.01
     only
    -1.01
     it
    -0.99
     from
    -0.98
     that
    -0.96
    POSITIVE LOGITS
     Россия
    1.36
     USA
    1.34
     России
    1.23
     США
    1.18
     Greece
    1.16
     България
    1.14
    Germany
    1.13
     Spain
    1.13
     Sweden
    1.08
     réput
    1.04
    Activations Density 0.083%

    No Known Activations