© 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. 10-GEMMASCOPE-RES-131K
    7. 47737
    Prev
    Next
    INDEX
    Explanations

    feelings and emotions

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

    The neuron flags words expressing emotional states or the verb “feel” (and its variants).

    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
    涐
    -1.60
    🌸
    -1.53
    嵓
    -1.52
     naše
    -1.51
     를
    -1.45
    評論
    -1.45
    🤌
    -1.43
    ‼
    -1.42
     basée
    -1.41
     Româ
    -1.41
    POSITIVE LOGITS
     such
    1.73
    5
    1.70
     a
    1.67
    6
    1.63
    しまい
    1.53
    8
    1.49
    1
    1.48
    比起
    1.40
    ↵↵↵
    1.38
    7
    1.31
    Activations Density 0.041%

    No Known Activations