© 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. 10-GEMMASCOPE-RES-131K
    7. 100980
    Prev
    Next
    INDEX
    Explanations

    next time you

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

    This neuron detects second-person temporal framing phrases—especially “next time you …” constructions.

    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
     milliards
    -1.34
    =
    -1.27
     habituellement
    -1.22
     immédiatement
    -1.21
     everything
    -1.21
     nien
    -1.20
    都需要
    -1.19
     comprenant
    -1.19
     dì
    -1.18
     recently
    -1.16
    POSITIVE LOGITS
     your
    1.46
    เรา
    1.41
     misschien
    1.38
     belki
    1.38
     vielleicht
    1.35
    我们的
    1.34
    мин
    1.23
     by
    1.23
     one
    1.23
     может
    1.22
    Activations Density 0.047%

    No Known Activations