© 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. 22-GEMMASCOPE-RES-131K
    7. 39674
    Prev
    Next
    INDEX
    Explanations

    technical or code snippets

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

    This neuron responds to the “break” keyword in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ahi
    -1.07
     cette
    -0.98
    colnshire
    -0.96
     této
    -0.94
    uei
    -0.90
    foni
    -0.90
    presa
    -0.89
     vivere
    -0.89
    dientes
    -0.88
    ieR
    -0.88
    POSITIVE LOGITS
    ஒ
    0.89
     utterly
    0.88
    kepada
    0.85
     think
    0.84
     completely
    0.84
    ,
    0.83
     (
    0.82
     quite
    0.82
     exploring
    0.81
     or
    0.80
    Activations Density 0.000%

    No Known Activations