© 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. 34-GEMMASCOPE-RES-131K
    7. 23476
    Prev
    Next
    INDEX
    Explanations

    dates and lists of things

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

    The neuron is specialized to detect numeric tokens (multi‐digit numbers and numerical figures) in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    protector
    -0.84
    SessionManager
    -0.77
     vya
    -0.77
     angekommen
    -0.76
    UIS
    -0.76
    Wp
    -0.75
     loggedIn
    -0.75
     demasiado
    -0.74
     physiotherapy
    -0.74
    Decomposition
    -0.73
    POSITIVE LOGITS
    riculares
    0.84
     Prato
    0.81
    利用
    0.78
    assade
    0.78
    epy
    0.74
    totalSupply
    0.74
     Roja
    0.74
    APPY
    0.73
    Operand
    0.73
    新型
    0.72
    Activations Density 0.001%

    No Known Activations