© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15494
    Prev
    Next
    INDEX
    Explanations

    for the purpose of

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

    This neuron detects instances where text states the purpose of something—especially the word “purpose” in constructions like “for the purpose of.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     mikina
    -1.68
    こだわり
    -1.67
     $^{\
    -1.63
     mundos
    -1.59
    ‶
    -1.58
    )]);
    -1.57
     capucha
    -1.55
    笮
    -1.55
    ૪
    -1.53
     pintadas
    -1.52
    POSITIVE LOGITS
    s
    2.42
     to
    2.31
     But
    2.03
    n
    2.02
     of
    1.84
     According
    1.84
     is
    1.81
    </em>
    1.75
     They
    1.75
    in
    1.67
    Activations Density 0.009%

    No Known Activations