© 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. 11811
    Prev
    Next
    INDEX
    Explanations

    what it is / how it works / why it works

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

    The neuron fires on capitalized standalone tokens—proper names, acronyms, and other uppercase or title‐case words.

    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
     스프
    0.65
    ocols
    0.61
    
    0.60
     बताऊंगा
    0.60
     vorstellen
    0.58
    Fill
    0.57
    )&&
    0.57
    ፂ
    0.56
    dotto
    0.55
    中有
    0.55
    POSITIVE LOGITS
    soever
    0.81
     they
    0.65
     he
    0.59
     они
    0.59
    கை
    0.57
     percent
    0.56
     (\%)
    0.56
     it
    0.55
    大家
    0.53
     вони
    0.52
    Activations Density 0.052%

    No Known Activations