© 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. 80847
    Prev
    Next
    INDEX
    Explanations

    just [determiner/number] [noun]

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

    The neuron fires on the common conversational “Just a …” introductory phrase (e.g. “Just a quick post,” “Just a thought experiment,” etc.).

    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
     コース
    -1.64
     autobus
    -1.48
     bandung
    -1.45
    prende
    -1.41
     剤
    -1.41
     your
    -1.40
     munich
    -1.39
     hjemmeside
    -1.39
    ｗｗ
    -1.38
     kien
    -1.38
    POSITIVE LOGITS
     “
    1.63
    Lots
    1.44
    ↵↵↵↵↵
    1.36
     ново
    1.35
    Fprintf
    1.33
    ?”
    1.32
     ol
    1.29
     incite
    1.27
    и
    1.25
    ↵↵↵↵↵↵↵
    1.24
    Activations Density 0.015%

    No Known Activations