© 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. 38988
    Prev
    Next
    INDEX
    Explanations

    international intrigue and historic sites

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

    The main thing this neuron does is detect numeric tokens (numbers, years, statistics, and other digit‐based expressions).

    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
     In
    -1.23
     If
    -1.07
     Because
    -1.06
     Some
    -1.06
     modest
    -1.05
    This
    -1.05
    The
    -1.02
     Since
    -1.00
    C
    -0.99
     More
    -0.98
    POSITIVE LOGITS
     conster
    1.15
     hant
    1.13
    اااا
    1.12
    伱
    1.11
     DÍA
    1.11
     kazak
    1.10
    اا
    1.09
     parachoque
    1.09
     rheumat
    1.07
     fuma
    1.07
    Activations Density 0.057%

    No Known Activations