© 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. 11368
    Prev
    Next
    INDEX
    Explanations

    one way to

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

    The neuron detects instructional “method introduction” phrases—e.g. “one way to…,” “two ways to…,” etc.—that introduce a suggested approach.

    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
    -3.20
    {
    -2.86
    2
    -2.73
    1
    -2.59
    '
    -2.36
    -
    -2.14
    3
    -2.06
    &
    -1.83
    4
    -1.81
    了一個
    -1.80
    POSITIVE LOGITS
    婿
    2.14
     of
    2.08
    杁
    2.00
    薙
    1.99
    mycin
    1.96
    TacToe
    1.93
     zlep
    1.91
    猹
    1.90
    zości
    1.90
    sistor
    1.90
    Activations Density 0.004%

    No Known Activations