© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44103
    Prev
    Next
    INDEX
    Explanations

    emotional states

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

    This neuron detects emotionally charged words—especially adjectives and participles that convey strong feelings or attitudes (e.g. confident, anxious, overwhelmed, excited).

    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
    茀
    -1.75
    ⟞
    -1.70
     expérimentés
    -1.56
     phénom
    -1.48
    ⼈
    -1.45
     éte
    -1.43
     réellement
    -1.41
    鄠
    -1.41
     parede
    -1.40
     lâmpada
    -1.40
    POSITIVE LOGITS
     or
    2.05
     and
    1.89
    $
    1.54
     such
    1.41
     in
    1.41
     on
    1.33
    änglich
    1.33
     other
    1.31
    2
    1.31
     changes
    1.27
    Activations Density 0.011%

    No Known Activations