© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10135
    Prev
    Next
    INDEX
    Explanations

    android operating system and devices

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

    The neuron is highly activated by occurrences of the word “Android,” i.e. mentions of the Android platform.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     infallible
    0.68
    భర
    0.64
    వ
    0.63
    ρης
    0.62
     갑
    0.60
    ρη
    0.57
    
    0.57
    సం
    0.57
     nécessaires
    0.56
    кр
    0.56
    POSITIVE LOGITS
    टरी
    0.59
    例
    0.58
    nnnn
    0.57
    spider
    0.57
    েলে
    0.57
    شهر
    0.57
    atian
    0.56
     Systematic
    0.56
     Blazers
    0.56
    )}>
    0.56
    Activations Density 0.020%

    No Known Activations