© 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. 11343
    Prev
    Next
    INDEX
    Explanations

    cannot and will not

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

    The neuron is especially sensitive to numeric and related metadata tokens—years, dates, reference numbers, and page‐navigation labels—essentially detecting structured numeric or UI boilerplate elements rather than normal prose.

    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
     Léon
    0.59
    ▬
    0.57
    ţie
    0.56
    Türk
    0.55
     Essays
    0.54
     Türk
    0.53
     ministère
    0.53
     nons
    0.52
     detrás
    0.51
     Yogyakarta
    0.51
    POSITIVE LOGITS
    낼
    0.62
     đc
    0.58
    aito
    0.55
     &=\
    0.55
    <0xE7>
    0.55
    ollary
    0.55
    佂
    0.54
    rl
    0.53
    내
    0.53
    ait
    0.53
    Activations Density 0.023%

    No Known Activations