© 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. 34-GEMMASCOPE-RES-131K
    7. 56771
    Prev
    Next
    INDEX
    Explanations

    afford to buy or not

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

    The neuron fires strongly on mentions of “can afford” or “can’t afford” constructions—that is, expressions about the ability (or inability) to afford something.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ataire
    -0.78
    øde
    -0.74
     Gloucester
    -0.72
     Schulz
    -0.71
    melden
    -0.71
     Zweig
    -0.71
     utilisez
    -0.71
    npj
    -0.71
     sujet
    -0.70
    ).)
    -0.70
    POSITIVE LOGITS
     afford
    5.34
    afford
    3.75
     affordability
    3.61
     Afford
    3.55
     affording
    3.34
     affordable
    3.13
     afforded
    2.98
     affords
    2.86
    affordable
    2.44
     Affordable
    2.39
    Activations Density 0.033%

    No Known Activations