© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60345
    Prev
    Next
    INDEX
    Explanations

    programming attributes and keywords

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

    The neuron fires on technical API identifiers related to attribute handling and object serialization (e.g. “attrs,” “AttributeSet,” “NSCoder,” “awakeFromNib”).

    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
    ”，
    -2.70
    0
    -2.27
    amazing
    -2.11
    颡
    -2.08
    Nous
    -1.95
    ”（
    -1.88
    剧照
    -1.86
     sist
    -1.82
    x
    -1.80
    麼
    -1.78
    POSITIVE LOGITS
    that
    2.83
     flesta
    2.11
     که
    2.11
    衚
    2.09
     что
    2.09
     fanns
    2.05
     cocin
    2.03
     econó
    2.00
     THAT
    1.98
    ––
    1.98
    Activations Density 0.000%

    No Known Activations