© 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. 128308
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on passive‐voice informational phrases of the form “is used by … to ….”

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

    permissions must be set to Allow for the area or iteration node

    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
     their
    -1.37
     occaf
    -1.26
     Tarif
    -1.24
     occafion
    -1.21
     ventre
    -1.17
     his
    -1.17
     reafon
    -1.16
    müş
    -1.14
     caufe
    -1.13
     fufficient
    -1.13
    POSITIVE LOGITS
     geralmente
    1.27
    Cartney
    1.27
    any
    1.20
    Materiál
    1.15
    This
    1.15
     encargado
    1.14
     berechtigt
    1.14
     Berufung
    1.13
    Any
    1.13
    が無い
    1.12
    Activations Density 0.000%

    No Known Activations