© 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. 41993
    Prev
    Next
    INDEX
    Explanations

    build scripts and libraries

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

    The neuron responds to lines that begin with substantial leading whitespace (i.e. indented code blocks).

    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
     the
    -2.20
    簠
    -2.06
    لباس
    -2.02
     鸭
    -2.02
    
    -2.00
    鑁
    -1.92
    鼷
    -1.90
     parachoque
    -1.88
    珰
    -1.84
     начале
    -1.79
    POSITIVE LOGITS
    It
    2.69
    There
    2.52
    The
    2.27
    If
    2.19
    They
    2.02
    1
    2.00
    依然
    1.98
    6
    1.95
     It
    1.92
     puzzling
    1.91
    Activations Density 0.001%

    No Known Activations