© 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. 15438
    Prev
    Next
    INDEX
    Explanations

    numbers and time

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

    The neuron strongly activates on numeric tokens (digits and 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
     teint
    -1.16
     criatura
    -1.16
     tatouage
    -1.16
    
    -1.16
     antropo
    -1.15
     murale
    -1.13
     eccl
    -1.13
     saumon
    -1.12
     sexe
    -1.10
     coloris
    -1.10
    POSITIVE LOGITS
     and
    1.83
    ઃ
    1.16
     when
    1.11
    CommonModule
    1.00
     xxi
    0.96
     titolata
    0.94
     agujero
    0.94
    nyard
    0.94
    tivazione
    0.93
     It
    0.93
    Activations Density 0.073%

    No Known Activations