© 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. 54054
    Prev
    Next
    INDEX
    Explanations

    closing code blocks and statements

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

    The neuron fires on statements that emit or log text (e.g. calls to Logger.info / print / println / echo).

    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
    ський
    -0.96
    oną
    -0.94
     científicas
    -0.92
    UnifiedTopology
    -0.91
    onomous
    -0.90
     defaults
    -0.89
     Defaults
    -0.88
    偽
    -0.88
     canción
    -0.88
     شيئ
    -0.87
    POSITIVE LOGITS
    Zdrav
    0.94
    ингл
    0.90
     ederim
    0.88
     negociaciones
    0.88
     chiama
    0.88
     aspetta
    0.86
     لكل
    0.86
     faceva
    0.85
     estaciones
    0.85
    urangi
    0.85
    Activations Density 0.001%

    No Known Activations