© 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. 846
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens representing decimal‐point measurements (i.e. 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
     सचिवा
    0.30
    हरू
    0.27
     الإنسان
    0.27
    wool
    0.26
    纜
    0.26
     adopté
    0.25
    嘅
    0.25
    clinton
    0.25
    ‑
    0.25
    :
    0.24
    POSITIVE LOGITS
     !(
    0.33
     maxWidth
    0.32
     Adapun
    0.31
     ArrayIndex
    0.29
    उनके
    0.29
     `:`,
    0.29
     Conversely
    0.29
     लेकिन
    0.29
     Despite
    0.29
     %><%=
    0.29
    Activations Density 0.064%

    No Known Activations