© 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. 106489
    Prev
    Next
    INDEX
    Explanations

    renewal and cancellation

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

    The neuron fires on prominent section or feature headings—i.e. the capitalized labels and titles used to mark major UI/menu sections.

    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
    velopment
    -0.93
     приви
    -0.81
     permits
    -0.81
     APPOINT
    -0.79
     reccomend
    -0.77
     לל
    -0.77
    护
    -0.77
     اخذ
    -0.76
     banho
    -0.76
     working
    -0.76
    POSITIVE LOGITS
     renewal
    1.46
     cancel
    1.46
    cancel
    1.37
    renewal
    1.32
     renewing
    1.29
     cancellation
    1.27
     billing
    1.25
     Cancel
    1.25
    Cancel
    1.24
     Renewal
    1.23
    Activations Density 0.028%

    No Known Activations