© 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. 93246
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis in multiple choice options

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

    The neuron activates on tokens that are numeric literals (digits and decimal 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
     parachoque
    -1.55
     anún
    -1.54
    dienne
    -1.49
    ～、
    -1.31
     onResume
    -1.31
     ideen
    -1.28
     defekt
    -1.28
    ༴
    -1.27
     که
    -1.27
     elevador
    -1.27
    POSITIVE LOGITS
    这是什么
    1.36
    …”
    1.24
    …?
    1.15
     
    1.12
     infor
    1.09
    ...?
    1.09
     немає
    1.05
     abol
    1.05
     condes
    1.03
     D
    1.02
    Activations Density 0.007%

    No Known Activations