© 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. 4150
    Prev
    Next
    INDEX
    Explanations

    code structure and values

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

    The neuron is strongly activated by “=” tokens and nearby variable‐ or property‐assignment constructs in code, i.e. assignment expressions.

    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
     it
    -0.98
    蛻
    -0.92
     لیے
    -0.88
    égias
    -0.87
     cosas
    -0.86
    rektur
    -0.86
     init
    -0.85
    出来ました
    -0.84
    cocina
    -0.84
    因为它
    -0.84
    POSITIVE LOGITS
     [],
    1.21
     {},
    1.13
    [],
    1.13
    False
    1.00
    false
    0.97
     his
    0.94
    nový
    0.93
    true
    0.93
     ourselves
    0.92
    nové
    0.92
    Activations Density 0.010%

    No Known Activations