© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43581
    Prev
    Next
    INDEX
    Explanations

    Text and code structure

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

    The neuron fires primarily on any contiguous four‐letter token.

    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
     it
    -1.95
     the
    -1.74
    More
    -1.60
     a
    -1.56
    鼉
    -1.51
    ↵
    -1.47
     zeigen
    -1.41
    ⚋
    -1.41
     erhöht
    -1.41
     ternura
    -1.40
    POSITIVE LOGITS
     alho
    1.75
    你
    1.73
    穑
    1.67
    le
    1.66
    翾
    1.64
    
    1.62
    na
    1.61
     hunne
    1.59
    ógicos
    1.55
    しました
    1.55
    Activations Density 0.000%

    No Known Activations