© 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. 95343
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

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

    The neuron detects references to routing or navigation APIs and libraries (e.g. “router,” “useHistory,” “SceneManagement,” “navigation,” etc.) 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
     from
    -0.81
     dunque
    -0.81
     Lauren
    -0.81
     dergleichen
    -0.81
    周泽
    -0.77
    ATTN
    -0.77
     Below
    -0.77
    Complications
    -0.76
     находятся
    -0.76
    geführten
    -0.76
    POSITIVE LOGITS
     térmica
    1.19
    ёг
    1.05
     området
    1.04
    mongoose
    1.03
    onViewCreated
    1.02
    centages
    1.01
    },[])
    1.00
     respirar
    0.99
    Areas
    0.98
     områ
    0.97
    Activations Density 0.001%

    No Known Activations