© 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. 65618
    Prev
    Next
    INDEX
    Explanations

    refuse, decline, reject

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

    The neuron activates strongly on numeric tokens (digits and numbers) in the text.

    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
     допуска
    -0.86
    ishu
    -0.79
    ophila
    -0.78
     oppress
    -0.78
    knn
    -0.78
     MAIL
    -0.77
     Adaptive
    -0.77
     reopened
    -0.77
     схе
    -0.74
    зы
    -0.73
    POSITIVE LOGITS
     declined
    3.97
     decline
    3.67
    拒绝
    3.59
     refusal
    3.56
     reject
    3.56
     rejection
    3.48
     rejecting
    3.47
     refused
    3.27
     rejected
    3.23
     refuse
    3.14
    Activations Density 0.049%

    No Known Activations