© 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. 34-GEMMASCOPE-RES-131K
    7. 59612
    Prev
    Next
    INDEX
    Explanations

    start of clauses

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

    This neuron fires on formal, bureaucratic or corporate/government‐style descriptive passages (e.g. definitions of agencies, official announcements, contractual responsibilities).

    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
    utete
    -0.87
     canada
    -0.84
     Federal
    -0.82
     canadian
    -0.81
    Federal
    -0.80
     Canadians
    -0.79
     Canadian
    -0.79
     oberen
    -0.79
     Daf
    -0.77
     Canada
    -0.76
    POSITIVE LOGITS
     ministry
    0.93
     tulisan
    0.83
     Ministry
    0.83
    Ministry
    0.80
     Getting
    0.79
     夜
    0.77
     statewide
    0.77
     microtub
    0.76
    randomNumber
    0.75
     Setting
    0.75
    Activations Density 0.031%

    No Known Activations