© 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. 22-GEMMASCOPE-RES-131K
    7. 39659
    Prev
    Next
    INDEX
    Explanations

    prime numbers and math questions

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

    The neuron strongly activates on software package names ending in “-dev,” i.e. tokens denoting developer‐library packages.

    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
    JAMIN
    -1.13
    。　
    -1.04
     voyez
    -1.03
    。　　
    -1.02
     voulez
    -1.00
     their
    -0.98
    大分
    -0.96
     trouverez
    -0.91
     саны
    -0.91
     devez
    -0.91
    POSITIVE LOGITS
    Pods
    1.03
    AutoScaleMode
    0.98
    fficients
    0.94
    랑
    0.92
     AKA
    0.91
    ễ
    0.91
    
    0.90
    ılıyor
    0.89
    Pasta
    0.89
     ร์
    0.89
    Activations Density 0.008%

    No Known Activations