© 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. 22-GEMMASCOPE-RES-131K
    7. 35571
    Prev
    Next
    INDEX
    Explanations

    plan to take action

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

    This neuron detects mentions of formal institutional or governmental actions (e.g. votes, plans, proposals, limits, announcements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     any
    -1.48
     with
    -1.46
     countless
    -1.44
     numerous
    -1.43
     many
    -1.43
     every
    -1.41
     both
    -1.41
     that
    -1.41
     usually
    -1.40
     other
    -1.39
    POSITIVE LOGITS
     ſte
    1.44
     prénom
    1.41
     juſ
    1.34
     trône
    1.34
     seuls
    1.33
     sirop
    1.32
     faſt
    1.32
     député
    1.30
     parfum
    1.28
     téléchargement
    1.28
    Activations Density 0.038%

    No Known Activations