© 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. 101980
    Prev
    Next
    INDEX
    Explanations

    explains or defines

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

    The neuron fires on occurrences of the word “mean” (and its inflections like “means” or “meaning”).

    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
     Gründe
    -1.56
    iſt
    -1.52
    毳
    -1.45
    
    -1.45
    秤
    -1.41
     yalnızca
    -1.40
     fehler
    -1.38
    ఏ
    -1.38
     設定
    -1.35
     сначала
    -1.35
    POSITIVE LOGITS
    </h3>
    1.91
    曁
    1.84
     that
    1.78
    "
    1.62
    es
    1.55
     menyen
    1.55
     ـ
    1.54
    ős
    1.52
    </u>
    1.52
    er
    1.48
    Activations Density 0.017%

    No Known Activations