© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93285
    Prev
    Next
    INDEX
    Explanations

    left boundary

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

    The neuron activates on programming-language tokens (keywords, symbols, numeric literals, and identifiers) typical of 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_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
    웠
    -0.87
    Peers
    -0.75
     Dism
    -0.74
    进入
    -0.73
    त्या
    -0.73
     Celeste
    -0.72
    Completo
    -0.71
     Sparse
    -0.69
     हूं
    -0.69
     Spie
    -0.69
    POSITIVE LOGITS
     left
    1.53
    left
    1.13
     Left
    1.11
    Left
    1.09
     LEFT
    1.05
    LEFT
    0.98
     low
    0.97
    getLeft
    0.94
    左右
    0.94
     startIndex
    0.90
    Activations Density 0.006%

    No Known Activations