© 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. 19623
    Prev
    Next
    INDEX
    Explanations

    Tomorrow

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

    The neuron selectively fires on the word “tomorrow,” marking mentions of the next-day temporal reference.

    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
    釭
    -3.09
    𖥦
    -3.03
    侂
    -2.81
    缃
    -2.78
     kursi
    -2.48
    荩
    -2.48
     ideen
    -2.44
    」,
    -2.44
     всѣ
    -2.41
    März
    -2.41
    POSITIVE LOGITS
    .
    2.67
    雳
    2.47
    StoryboardSegue
    2.42
    u
    2.38
    蓥
    2.31
     disponer
    2.30
     Then
    2.20
     Roughly
    2.14
     Tomorrow
    2.14
    ↵
    2.11
    Activations Density 0.003%

    No Known Activations