© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 932
    Prev
    Next
    INDEX
    Explanations

    neural network architectures

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

    This neuron detects numeric tokens representing floating‐point values (decimal 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_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
    ȋ
    0.63
    ición
    0.59
    úra
    0.57
    ineuses
    0.57
     ভুট্টোর
    0.57
    ïd
    0.56
    āna
    0.56
    ıma
    0.55
    iciência
    0.55
     কম্পিউ
    0.55
    POSITIVE LOGITS
     Mereka
    0.52
    এটি
    0.49
     the
    0.47
    অধ
    0.46
    ↵↵
    0.45
     Das
    0.45
    𝖊
    0.45
    Das
    0.44
    これで
    0.44
     hogar
    0.44
    Activations Density 0.000%

    No Known Activations