© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73857
    Prev
    Next
    INDEX
    Explanations

    multiple options or difficulty

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

    The neuron is keyed to verbs (often Chinese function verbs like “是,” “会,” “回,” “处理” or English verbs like “mapping,” “return,” “transfer”) that describe operations or actions.

    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
     neither
    -0.89
    UnitTesting
    -0.87
     иногда
    -0.87
    1
    -0.87
     none
    -0.87
     seems
    -0.84
    RTLD
    -0.84
    J
    -0.82
    Л
    -0.80
    不高
    -0.79
    POSITIVE LOGITS
     开发
    0.93
    繻
    0.92
     cán
    0.92
     rostros
    0.91
    sees
    0.89
    theres
    0.88
    `:
    0.87
     magaz
    0.87
    ...-
    0.87
    materials
    0.87
    Activations Density 0.001%

    No Known Activations