© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35304
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical expressions

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

    The neuron is primarily activating on numeric tokens (numbers and numeric-like strings).

    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
     make
    -1.13
     possibly
    -1.05
    After
    -1.03
     offered
    -1.03
     After
    -0.99
     probably
    -0.99
     gives
    -0.98
     going
    -0.98
     give
    -0.96
     makes
    -0.96
    POSITIVE LOGITS
     anonym
    1.00
    
    0.98
    ensitive
    0.96
    žku
    0.94
    黢
    0.94
     différentes
    0.94
    畋
    0.94
    绺
    0.94
    を変える
    0.94
    believe
    0.93
    Activations Density 0.061%

    No Known Activations