© 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. 67384
    Prev
    Next
    INDEX
    Explanations

    future time and events

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

    The neuron activates on words and phrases that signal future events or planned actions (e.g., coming, planning, will, release).

    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
     parfois
    -1.20
     quelquefois
    -0.94
    ciuto
    -0.88
     nästan
    -0.87
    แรก
    -0.86
     carreaux
    -0.84
     てき
    -0.84
    []){
    -0.83
    ag
    -0.83
     telah
    -0.83
    POSITIVE LOGITS
     soon
    2.33
     someday
    1.92
     sooner
    1.59
     Soon
    1.41
    Soon
    1.38
    soon
    1.38
     veremos
    1.33
     SOON
    1.30
     eventually
    1.25
     скоро
    1.25
    Activations Density 0.045%

    No Known Activations