© 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. 3813
    Prev
    Next
    INDEX
    Explanations

    action followed by progression

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

    The neuron strongly activates on modal and future‐oriented function words (e.g. may, will, to, likely, expected), i.e. markers of speculation or upcoming actions.

    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
     capteur
    -1.59
    趿
    -1.50
     chô
    -1.42
    僰
    -1.41
     plafon
    -1.41
     varier
    -1.40
     ['./
    -1.40
     fallu
    -1.39
     ไม่มี
    -1.38
     provenant
    -1.36
    POSITIVE LOGITS
     more
    2.58
     as
    2.03
     some
    2.02
     in
    1.91
     further
    1.79
     big
    1.73
     soon
    1.66
     out
    1.65
     well
    1.65
     many
    1.64
    Activations Density 0.123%

    No Known Activations