© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65112
    Prev
    Next
    INDEX
    Explanations

    bringing back something

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

    The neuron activates on occurrences of the word “back” (as in bring back, brought back, back to, etc.), signaling mentions of returning or restoring something.

    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
     you
    -1.87
    蹿
    -1.78
    isière
    -1.74
    描いた
    -1.70
    栳
    -1.68
    
    -1.67
    そりゃ
    -1.64
    ブログ村
    -1.63
     IBOutlet
    -1.62
    戆
    -1.62
    POSITIVE LOGITS
    ’
    2.50
    自身
    1.81
    她
    1.59
     –
    1.58
    u
    1.56
     ‘’
    1.56
    ਤ
    1.55
    主要
    1.55
    ：
    1.54
    o
    1.53
    Activations Density 0.004%

    No Known Activations