© 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. 22-GEMMASCOPE-RES-131K
    7. 9622
    Prev
    Next
    INDEX
    Explanations

    numerous items

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

    The neuron strongly activates on the word “Numerous,” essentially detecting that specific token wherever it appears.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    了一些
    -2.34
    2
    -2.08
     glimpses
    -2.02
    でも
    -1.99
    我又
    -1.88
    戆
    -1.87
    や
    -1.86
    𖣔
    -1.84
    𓁹
    -1.81
    ༷
    -1.81
    POSITIVE LOGITS
     Their
    3.14
    mente
    2.19
    f
    2.16
     They
    2.16
    n
    2.06
     közül
    2.03
    r
    2.02
    哒
    1.99
    
    1.91
    '
    1.90
    Activations Density 0.007%

    No Known Activations