© 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. 19841
    Prev
    Next
    INDEX
    Explanations

    software libraries and services

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

    The neuron fires on the names of software libraries or frameworks (e.g. RecyclerView, Firestore, Elasticsearch).

    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
    1
    -2.95
    $
    -2.89
    8
    -2.88
    2
    -2.72
    9
    -2.69
    6
    -2.52
    𐐪
    -2.50
    7
    -2.42
    i
    -2.36
    3
    -2.36
    POSITIVE LOGITS
    
    3.48
    我们就
    3.13
    衚
    3.09
    艄
    2.84
    ⑊
    2.83
    聍
    2.73
    锜
    2.67
    StoryboardSegue
    2.67
    pped
    2.58
    ⟞
    2.56
    Activations Density 0.004%

    No Known Activations