© 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. 10199
    Prev
    Next
    INDEX
    Explanations

    \begin{document}

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

    The neuron is activated by standalone numeric tokens with decimal points (floating‐point numbers).

    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
    documentclass
    0.58
    ]/*
    0.50
     &=
    0.50
    /*
    0.48
    androidTest
    0.48
    simeq
    0.48
    sqrt
    0.47
    NotFound
    0.46
    bigcirc
    0.46
    ');//
    0.46
    POSITIVE LOGITS
     カーボン
    0.65
     decirlo
    0.61
     пробле
    0.59
     パール
    0.59
    afety
    0.58
     milieu
    0.58
     predatory
    0.58
     कहलाती
    0.58
     осіб
    0.57
     విషయ
    0.57
    Activations Density 0.000%

    No Known Activations