© 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. 34-GEMMASCOPE-RES-131K
    7. 34900
    Prev
    Next
    INDEX
    Explanations

    common multiple

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

    The neuron strongly activates on programming‐related tokens and identifiers (i.e. code snippets) in the text.

    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
     burst
    -0.85
     vivid
    -0.82
     bursts
    -0.77
     pops
    -0.77
    Dama
    -0.76
    Broke
    -0.74
    Walla
    -0.73
     dama
    -0.72
     Dama
    -0.70
     popped
    -0.70
    POSITIVE LOGITS
     Umbra
    1.23
    umb
    1.04
     umb
    1.00
     superfí
    0.87
    Ƨ
    0.84
    AIDS
    0.82
     instruções
    0.82
     doces
    0.82
     恤
    0.82
     preço
    0.81
    Activations Density 0.017%

    No Known Activations