© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10091
    Prev
    Next
    INDEX
    Explanations

    code blocks `{}`

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

    The neuron is looking for numeric tokens containing 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_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
    ңа
    0.75
    ⟧
    0.74
    लाई
    0.73
    Longrightarrow
    0.73
     exemplified
    0.70
     زیاد
    0.70
     እንደሚ
    0.69
    '][
    0.69
    玴
    0.68
    asted
    0.67
    POSITIVE LOGITS
     trak
    0.84
    elje
    0.79
     pione
    0.77
     raken
    0.76
     votos
    0.76
     kontak
    0.75
     Tjiwarl
    0.75
     blotting
    0.74
     Kontak
    0.74
     vrata
    0.73
    Activations Density 0.001%

    No Known Activations