© 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. 22-GEMMASCOPE-RES-131K
    7. 66265
    Prev
    Next
    INDEX
    Explanations

    being part of a group

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

    The neuron fires strongly on tokens naming interconnected systems or infrastructures (e.g. grid, network, chain, train, bus).

    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
     daraus
    -0.91
     Bekannt
    -0.89
     legislación
    -0.87
     cố
    -0.85
     Durchführung
    -0.84
     between
    -0.84
    に来て
    -0.83
    aria
    -0.82
    Cov
    -0.81
     Collect
    -0.80
    POSITIVE LOGITS
     membership
    1.74
    membership
    1.45
    Membership
    1.27
     memberships
    1.17
     Membership
    1.16
     MEMBERSHIP
    1.09
    participation
    1.09
     participation
    1.06
     enrolment
    1.03
    enrollment
    1.02
    Activations Density 0.094%

    No Known Activations