© 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. 127695
    Prev
    Next
    INDEX
    Explanations

    activities and experiences

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

    The neuron detects action words—especially gerund/-ing forms—denoting engagement with or consumption of content (e.g. reading, listening, watching, enjoying).

    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
         
    -1.45
    -1.44
     FIRST
    -1.43
              
    -1.40
        
    -1.40
     BY
    -1.39
     SHOULD
    -1.36
     need
    -1.36
     necesitar
    -1.35
     gleiche
    -1.34
    POSITIVE LOGITS
    yfik
    1.41
     sista
    1.38
     homoto
    1.38
    ☕️
    1.35
    viewType
    1.34
     pilla
    1.33
     joel
    1.33
     Xn
    1.33
     サー
    1.30
     Irlanda
    1.30
    Activations Density 0.011%

    No Known Activations