© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5143
    Prev
    Next
    INDEX
    Explanations

    `self` or `my` followed by `.`, `with_`, or `_`

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

    The neuron strongly activates on numeric literals (especially floating-point numbers) embedded in code or JSON.

    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_24_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
     ,
    0.70
    in
    0.63
     multimillion
    0.62
      
    0.61
     vying
    0.61
     μιας
    0.60
    ization
    0.59
     coffers
    0.59
     wraz
    0.58
     굉장히
    0.57
    POSITIVE LOGITS
    datasets
    0.59
    行的
    0.58
    えた
    0.55
    𝙇
    0.52
     வாழைப்பழ
    0.52
     continueRoutine
    0.50
    াহতি
    0.50
    َد
    0.49
    getCql
    0.49
     exons
    0.49
    Activations Density 0.000%

    No Known Activations