© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73178
    Prev
    Next
    INDEX
    Explanations

    ages

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

    The neuron strongly activates on numeric tokens (multi‐digit numbers, e.g. years, ages, identifiers).

    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
     this
    -1.33
     it
    -1.30
     either
    -1.14
     each
    -1.14
     place
    -1.08
     όμως
    -1.05
    　　「
    -1.05
     everything
    -1.02
     comércio
    -0.97
    ニュアル
    -0.97
    POSITIVE LOGITS
     who
    1.45
    rildi
    1.16
     její
    1.13
     beslu
    1.12
    
    1.09
     ที่
    1.00
    ೃ
    0.99
     már
    0.99
    iseksi
    0.99
     vorige
    0.98
    Activations Density 0.011%

    No Known Activations