© 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. 59944
    Prev
    Next
    INDEX
    Explanations

    purpose of something

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

    The neuron strongly activates on occurrences of the word “purpose” (especially in the phrase “purpose-built”).

    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
     мнению
    -1.10
     copious
    -1.05
    ers
    -1.00
     сравнению
    -0.99
     prolonged
    -0.96
    なんでも
    -0.96
     focuses
    -0.95
    acyj
    -0.93
     multitude
    -0.93
     antiguas
    -0.93
    POSITIVE LOGITS
    Purpose
    1.66
     purpose
    1.58
    purpose
    1.56
    fulness
    1.45
    ful
    1.34
     Purposes
    1.34
     Purpose
    1.30
    fully
    1.21
    FUL
    1.17
    用途
    1.13
    Activations Density 0.026%

    No Known Activations