© 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. 22-GEMMASCOPE-RES-131K
    7. 130933
    Prev
    Next
    INDEX
    Explanations

    The neuron detects terms related to setting or pursuing goals and plans.

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

    setting goals and objectives

    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
     brune
    -1.40
    Особенности
    -1.21
     rett
    -1.16
     stiller
    -1.16
     fatale
    -1.15
    Choices
    -1.15
     tradis
    -1.14
     speel
    -1.13
     作り方
    -1.10
     inond
    -1.10
    POSITIVE LOGITS
     goals
    2.69
     goal
    2.17
     objectives
    1.77
     targets
    1.66
    目標
    1.59
     target
    1.50
    目标
    1.47
    Goal
    1.44
     achievable
    1.43
     hedef
    1.42
    Activations Density 0.017%

    No Known Activations