© 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. 34-GEMMASCOPE-RES-131K
    7. 63922
    Prev
    Next
    INDEX
    Explanations

    sequel

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

    The neuron is primarily activated by standalone numeric tokens (especially single‐digit 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_34/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
     thơ
    -0.84
     plucked
    -0.82
     Composite
    -0.79
    uctura
    -0.78
     recientes
    -0.77
     rashes
    -0.76
     cómoda
    -0.75
    瓠
    -0.75
    はじめて
    -0.75
     vuestra
    -0.73
    POSITIVE LOGITS
     sequel
    5.53
     sequels
    4.03
     Sequel
    3.31
    sequ
    3.25
    Sequ
    2.83
     follow
    2.47
     sequ
    2.45
    続
    2.45
    续
    2.42
    續
    2.42
    Activations Density 0.060%

    No Known Activations