© 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. 72499
    Prev
    Next
    INDEX
    Explanations

    interpersonal and organizational contexts

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

    The neuron fires on common multiword connective filler phrases made up of high-frequency function words (e.g. “but to the …,” “couple that with …”).

    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
     Dunes
    -0.89
    뺀
    -0.85
     FOOTBALL
    -0.84
    football
    -0.82
    any
    -0.81
     Tada
    -0.81
    Profession
    -0.81
    zustellen
    -0.80
    both
    -0.79
    zi
    -0.78
    POSITIVE LOGITS
     social
    1.17
     also
    1.05
     administrativa
    1.01
     interpersonal
    1.00
     administrative
    1.00
     moral
    0.97
     personality
    0.96
     relationships
    0.95
     emotional
    0.93
     organizational
    0.93
    Activations Density 0.111%

    No Known Activations