© 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. 6798
    Prev
    Next
    INDEX
    Explanations

    loyalty or PDA

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

    The neuron strongly activates on occurrences of “loyalty” (especially in contexts like customer or brand loyalty and loyalty programs).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     französische
    -2.42
     interestingly
    -2.41
     This
    -2.39
     undoubtedly
    -2.36
     There
    -2.31
    brainly
    -2.30
     surprisingly
    -2.28
     impressively
    -2.23
     thankfully
    -2.23
     ironically
    -2.22
    POSITIVE LOGITS
    _
    2.83
    the
    2.80
    s
    2.72
    they
    2.70
    their
    2.42
    those
    2.36
    provide
    2.36
    焄
    2.31
     avait
    2.28
    作って
    2.28
    Activations Density 0.004%

    No Known Activations