© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80835
    Prev
    Next
    INDEX
    Explanations

    positive feelings or strong opinions

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

    The neuron activates on occurrences of the verb “feel” (in forms like feel/feels), marking expressions of personal sensation or sentiment.

    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
    grö
    -0.94
     interesses
    -0.93
     PowerShell
    -0.93
    ᑎ
    -0.91
    тут
    -0.91
    🏒
    -0.91
     évalu
    -0.89
    rufe
    -0.89
    надца
    -0.89
    tod
    -0.89
    POSITIVE LOGITS
     strongly
    2.02
     it
    1.81
     there
    1.65
     that
    1.59
     feel
    1.57
     confident
    1.43
    Strongly
    1.34
     strong
    1.30
     this
    1.27
     comfortable
    1.27
    Activations Density 0.011%

    No Known Activations