© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71436
    Prev
    Next
    INDEX
    Explanations

    function arguments, calls, or types

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

    The neuron fires on tokens that are (or contain) integer 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
    着脸
    -1.09
    ÍNDICE
    -1.07
    ഃ
    -1.05
    centra
    -1.01
    😂😂😂😂
    -0.99
     también
    -0.97
     chande
    -0.96
    ଘ
    -0.96
     nicolas
    -0.96
    Also
    -0.93
    POSITIVE LOGITS
     first
    1.58
    1
    1.27
    0
    1.19
     here
    1.12
     only
    1.11
     pertama
    1.08
     första
    1.06
    puerto
    1.05
    2
    1.04
     former
    1.03
    Activations Density 0.010%

    No Known Activations