© 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. 9653
    Prev
    Next
    INDEX
    Explanations

    dates and specific entities

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

    The neuron activates on numeric tokens or digit‐containing strings (especially prices, quantities, dates, and other 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
     propuestas
    -1.13
    often
    -0.99
    ru
    -0.93
    ⏤
    -0.93
     relevant
    -0.93
     discussion
    -0.91
     אֶ
    -0.90
     necesario
    -0.90
    []=$
    -0.90
     particular
    -0.88
    POSITIVE LOGITS
     will
    1.74
     before
    1.26
     minggu
    1.25
     November
    1.12
     confirme
    1.06
     шокола
    1.04
    itaries
    1.04
     October
    1.02
     elseif
    1.02
     during
    1.01
    Activations Density 0.010%

    No Known Activations