© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14099
    Prev
    Next
    INDEX
    Explanations

    university or place names

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

    the neuron activates on numeric tokens and punctuation in numbers (digits, decimals, years, and numeric citations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ayudará
    -1.20
    がある
    -1.20
     които
    -1.16
     которые
    -1.12
    があり
    -1.09
     nieuwe
    -1.08
     permettra
    -1.08
     щодо
    -1.07
     иллюстрация
    -1.03
    があります
    -1.02
    POSITIVE LOGITS
     Auffassung
    0.97
    Orsay
    0.96
    метров
    0.96
    Beschrijving
    0.95
    øb
    0.93
     һ
    0.90
    RESUMEN
    0.90
    Both
    0.90
     inode
    0.89
    دخ
    0.89
    Activations Density 0.099%

    No Known Activations