© 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. 26072
    Prev
    Next
    INDEX
    Explanations

    various numerical and symbolic sequences

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

    The neuron activates on tokens that are numeric values (especially two-digit numbers).

    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
     Gennaio
    -1.23
     which
    -1.21
    wego
    -1.18
    ‼
    -1.09
     Giugno
    -1.08
    mosis
    -1.07
    🤨
    -1.06
     =(
    -1.05
     kraf
    -1.05
     обувь
    -1.03
    POSITIVE LOGITS
     riesgo
    1.19
    佼
    1.02
    cesta
    1.01
     entsprechen
    0.99
     trám
    0.95
    inven
    0.94
     oes
    0.94
     récemment
    0.94
    bandit
    0.94
     waarschijnlijk
    0.93
    Activations Density 0.001%

    No Known Activations