© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73591
    Prev
    Next
    INDEX
    Explanations

    references

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

    The neuron fires on isolated numeric tokens—years, dates, and other standalone numbers.

    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
     gangen
    -1.11
    section
    -1.03
    //{
    
    -1.02
    NORE
    -1.02
     ส์
    -1.00
    。
    -0.96
    docx
    -0.96
    ᴀ
    -0.95
    N
    -0.94
     usada
    -0.94
    POSITIVE LOGITS
    geox
    1.27
    camis
    1.24
     to
    1.22
    boho
    1.22
    turkish
    1.19
    afro
    1.17
    mitsubishi
    1.15
    harley
    1.14
    regi
    1.13
    hyundai
    1.12
    Activations Density 0.006%

    No Known Activations