© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6999
    Prev
    Next
    INDEX
    Explanations

    authorities and official roles

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

    The neuron is tuned to spot numeric tokens or figures (e.g. multi‐digit numbers, percentages, measurements).

    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
    siswa
    0.70
    काच्या
    0.64
     어린
    0.62
    自身
    0.60
    ريع
    0.60
    木
    0.59
    Revelation
    0.59
    as
    0.58
     rakyat
    0.58
    、
    0.57
    POSITIVE LOGITS
     autoridades
    1.09
     authorities
    1.03
     autorités
    0.94
     superiors
    0.94
     administrators
    0.91
     কর্তৃপক্ষ
    0.91
     работода
    0.86
     policymakers
    0.84
     autorità
    0.81
     supervisors
    0.80
    Activations Density 0.338%

    No Known Activations