© 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. 22-GEMMASCOPE-RES-131K
    4. 35950
    Prev
    Next
    INDEX
    Explanations

    return, deliver, redirect

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

    The neuron activates on words indicating returning or delivering a value (e.g. “return,” “returned,” “delivered”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     peringatan
    -0.93
     puisi
    -0.93
    atów
    -0.91
    bouton
    -0.91
    bạn
    -0.90
    
    -0.90
    ξύ
    -0.89
    Redacción
    -0.88
     folhe
    -0.88
     inspiração
    -0.88
    POSITIVE LOGITS
     return
    1.56
     this
    1.36
     after
    1.21
     what
    1.12
    return
    1.10
     result
    1.09
     or
    1.06
    anova
    1.04
     here
    1.04
     good
    1.02
    Activations Density 0.007%

    No Known Activations