© 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. 116045
    Prev
    Next
    INDEX
    Explanations

    programming types

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

    The neuron fires on object‐property definitions in code—especially the prop/type/default declarations in a Vue component’s props block.

    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
     ventre
    -0.91
     organisme
    -0.85
    брав
    -0.82
    بیش
    -0.78
    税込
    -0.77
    íram
    -0.77
    Затем
    -0.77
    erschein
    -0.77
    REFERENCE
    -0.72
     cilind
    -0.72
    POSITIVE LOGITS
     viena
    1.02
     any
    0.84
     vroe
    0.83
     prop
    0.81
    \}\
    0.81
    솟
    0.78
    ähig
    0.78
    typeDefinition
    0.77
    antenna
    0.75
    rhythm
    0.75
    Activations Density 0.013%

    No Known Activations