© 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. 80971
    Prev
    Next
    INDEX
    Explanations

    return value or item

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

    The neuron strongly activates on the token “Return” (and its immediate context), i.e. headings or commands starting with “Return.”

    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
     Entsch
    -0.99
     مدیر
    -0.90
    ล้ว
    -0.87
    Que
    -0.86
    Six
    -0.85
    日を
    -0.84
    Seven
    -0.83
    Cir
    -0.83
     le
    -0.82
    additional
    -0.82
    POSITIVE LOGITS
     RETURN
    1.22
     Return
    1.22
     trip
    1.21
     Merchandise
    1.11
     Returns
    1.02
    artige
    0.98
    の山
    0.98
    razi
    0.97
     Journey
    0.96
     chamada
    0.94
    Activations Density 0.021%

    No Known Activations