© 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. 80931
    Prev
    Next
    INDEX
    Explanations

    redistribute or modify

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

    The neuron activates on programming‐language syntax elements (e.g. dots, parentheses, keywords like “if” and other code punctuation).

    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
     facilitating
    -0.81
     jamón
    -0.81
    vědět
    -0.75
     Herv
    -0.73
     Hols
    -0.73
     chết
    -0.73
    myapp
    -0.73
    München
    -0.71
     patatas
    -0.71
     comentó
    -0.71
    POSITIVE LOGITS
     Administração
    0.92
    next
    0.78
    ederen
    0.77
    AccessFile
    0.77
    <0x94>
    0.76
    ばら
    0.75
    know
    0.74
    THER
    0.74
    جعل
    0.73
     tableta
    0.73
    Activations Density 0.003%

    No Known Activations