© 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. 10-GEMMASCOPE-RES-131K
    7. 70357
    Prev
    Next
    INDEX
    Explanations

    "description"

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

    The neuron fires on occurrences of the field or key name “description” in structured data or 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_10/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
    旆
    -2.25
    樒
    -2.11
    蓠
    -2.08
    ⎆
    -2.05
    enablog
    -2.05
    凩
    -2.03
    嵛
    -1.98
    ⸂
    -1.97
     lauded
    -1.92
    鸲
    -1.84
    POSITIVE LOGITS
    ’
    3.00
    ↵
    2.80
    “
    2.72
    ‘
    2.31
    .”
    2.22
    m
    2.09
     “
    1.99
    ，“
    1.87
     \
    1.85
     ‘
    1.84
    Activations Density 0.054%

    No Known Activations