© 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. 7498
    Prev
    Next
    INDEX
    Explanations

    Java code structure: class, public

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

    The neuron fires on the character sequence “Tan” in capitalized names.

    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
     dirt
    0.75
    dirt
    0.65
    Dirt
    0.61
     गंदगी
    0.61
    흙
    0.59
     Dirt
    0.57
    ান্ড
    0.56
     dusty
    0.56
     dirty
    0.55
    ativer
    0.55
    POSITIVE LOGITS
    莗
    0.58
     Serialize
    0.55
    榞
    0.54
     Pawar
    0.51
     Junio
    0.49
     装
    0.48
     Reuters
    0.47
     Promoting
    0.46
     IEEE
    0.46
    渲
    0.46
    Activations Density 0.001%

    No Known Activations