© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2512
    Prev
    Next
    INDEX
    Explanations

    approve or authorize actions

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

    The neuron fires on formal governmental or bureaucratic decision language (e.g. “approved,” “authorized,” “resolution,” “adopt”).

    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
    discover
    -0.79
     descub
    -0.77
    gitto
    -0.74
    iesis
    -0.74
     musí
    -0.74
     meetings
    -0.73
    ayaquil
    -0.73
     梅
    -0.73
     подчер
    -0.72
    cienza
    -0.71
    POSITIVE LOGITS
     approve
    1.17
     purchase
    1.14
     recommended
    1.02
     increase
    1.02
     proposed
    1.02
     revised
    1.00
    purchase
    0.97
    changes
    0.97
    modified
    0.96
     authorization
    0.96
    Activations Density 0.039%

    No Known Activations