© 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. 10-GEMMASCOPE-RES-131K
    7. 29028
    Prev
    Next
    INDEX
    Explanations

    move on to

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

    The neuron detects occurrences of the phrase “move on” (including its inflected forms) signaling transition or progression.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    0
    -1.93
     innymi
    -1.84
    gucig
    -1.68
    𝘳
    -1.66
    見えない
    -1.66
     wiesz
    -1.63
    </i>
    -1.63
     móg
    -1.62
     一覧
    -1.61
     LEGEND
    -1.58
    POSITIVE LOGITS
    ☫
    1.99
    ."
    1.95
    ?
    1.91
    媜
    1.90
    他
    1.89
     In
    1.84
    天津
    1.84
     "
    1.74
     refurbished
    1.73
    。
    1.70
    Activations Density 0.005%

    No Known Activations