© 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. 13125
    Prev
    Next
    INDEX
    Explanations

    enjoying activities

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

    The neuron fires on expressions of personal enjoyment or liking—particularly the verb “enjoy” (and its inflected forms).

    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
    -2.50
     they
    -2.31
    i
    -2.09
     Those
    -1.95
     our
    -1.94
    with
    -1.84
     usual
    -1.84
    New
    -1.84
     Probably
    -1.81
    ....
    -1.76
    POSITIVE LOGITS
    亖
    1.98
    
    1.98
    rufen
    1.91
    這
    1.89
     dieß
    1.89
    ྅
    1.88
    альных
    1.88
     twa
    1.81
    蕖
    1.81
    ᕱ
    1.80
    Activations Density 0.014%

    No Known Activations