© 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. 34-GEMMASCOPE-RES-131K
    7. 2146
    Prev
    Next
    INDEX
    Explanations

    introduces meaning or consequence

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

    The neuron detects occurrences of the word “mean” or “means” (and its immediate helpers like “that” or “which”) when used to introduce an explanatory or inferential phrase.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ControllerAdvice
    -0.86
    cześ
    -0.80
    なぜ
    -0.79
    称呼
    -0.77
    走る
    -0.77
    enzio
    -0.76
    irut
    -0.75
    wsze
    -0.75
    碜
    -0.75
    unsplash
    -0.74
    POSITIVE LOGITS
     means
    7.75
     meaning
    5.88
    means
    5.72
     mean
    5.41
     Means
    5.28
    Means
    5.13
     значит
    4.81
     означает
    4.66
     significa
    4.56
     bedeutet
    4.56
    Activations Density 0.393%

    No Known Activations