© 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. 1328
    Prev
    Next
    INDEX
    Explanations

    words starting with a vowel sound

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

    The neuron is highly responsive to numeric tokens, especially floating-point numbers (numbers with decimals).

    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
     Eligible
    0.38
    <unused436>
    0.38
    <unused2157>
    0.38
     adlı
    0.38
     Agricultura
    0.37
     ausschließlich
    0.37
     Ubuy
    0.37
     ܥ
    0.36
     exclusivamente
    0.36
     Tugas
    0.36
    POSITIVE LOGITS
     bunch
    0.50
     madness
    0.50
     nice
    0.48
     lot
    0.48
     glimpse
    0.47
     flair
    0.47
     reprieve
    0.47
     clue
    0.46
     good
    0.46
     few
    0.46
    Activations Density 0.091%

    No Known Activations