© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12837
    Prev
    Next
    INDEX
    Explanations

    when introducing a circumstance

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

    The neuron flags strong emotional-reaction words (e.g. surprised, excited, offended, shocked).

    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
     a
    -2.08
     also
    -1.42
     dessutom
    -1.40
     vermelha
    -1.36
     amarela
    -1.31
    xvii
    -1.29
      
    -1.29
     inland
    -1.27
     had
    -1.27
    []):
    -1.23
    POSITIVE LOGITS
    颪
    1.54
    ︕
    1.46
     vasi
    1.45
     formen
    1.41
     vernac
    1.41
    慙
    1.38
     rik
    1.37
     giocare
    1.36
     kaos
    1.35
    などは
    1.34
    Activations Density 0.017%

    No Known Activations