© 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. 67701
    Prev
    Next
    INDEX
    Explanations

    URL, email, login

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

    The neuron predominantly activates on numeric tokens (integer values or multi‐digit numbers) in the 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_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
     they
    -1.10
     TAMBÉM
    -1.09
    cipital
    -1.05
     what
    -0.99
     how
    -0.98
     with
    -0.97
    一面
    -0.97
     the
    -0.96
    鎔
    -0.96
     &
    -0.95
    POSITIVE LOGITS
      
    1.08
    ∆
    1.05
     ,'
    1.04
    
    1.03
    She
    1.03
    烬
    1.02
    Χ
    1.01
    ⡦
    1.01
    ©
    1.00
     hendes
    1.00
    Activations Density 0.050%

    No Known Activations