© 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. 9317
    Prev
    Next
    INDEX
    Explanations

    rumbling, rumination, Romaine, Romwe

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

    The neuron strongly activates on tokens that are floating-point numbers (decimal numerals), i.e. numeric sequences with a decimal point.

    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
    fwlink
    0.62
    )";
    0.58
    ὔ
    0.57
    стаў
    0.56
    год
    0.55
     गर्व
    0.53
     linguaggio
    0.53
    
    0.53
    )`;
    0.52
     ওয়ালপেপার
    0.52
    POSITIVE LOGITS
    部位
    0.63
     Taking
    0.60
    Taking
    0.59
    ্কার
    0.57
     multilayer
    0.55
    ơi
    0.54
     yêu
    0.52
     viscosity
    0.51
    โบ
    0.51
     Sui
    0.50
    Activations Density 0.004%

    No Known Activations