© 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. 7544
    Prev
    Next
    INDEX
    Explanations

    programming languages and libraries

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

    The neuron activates on numeric and version‐style tokens (e.g. library versions, package numbers, configuration values).

    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
    🫶
    1.31
    🥹
    1.22
    🫠
    1.22
    🥲
    1.16
     tiktok
    1.15
     TikTok
    1.14
    🥰
    1.13
     २०२२
    1.10
    🫰
    1.10
    🩷
    1.10
    POSITIVE LOGITS
     componentWill
    0.96
     ২০১৬
    0.90
     ২০১৭
    0.78
     xrange
    0.78
     ২০১৫
    0.72
     batsmen
    0.71
     Flücht
    0.71
     AdWords
    0.71
    PropTypes
    0.70
     ব্যাটসম্যান
    0.70
    Activations Density 0.009%

    No Known Activations