© 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. 12674
    Prev
    Next
    INDEX
    Explanations

    polka dots, toothpaste, forgetting

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

    The neuron flags uncommon or domain‐specific tokens—particularly longer proper nouns, technical terms, or otherwise low-frequency/unusual words.

    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
     a
    -3.25
    in
    -2.64
    𓆜
    -2.58
    ↵
    -2.53
    必要な
    -2.45
    也会
    -2.36
    赑
    -2.34
    FundMe
    -2.19
    ⸒
    -2.19
    just
    -2.16
    POSITIVE LOGITS
    姈
    2.80
    苙
    2.77
    瑆
    2.66
    borderSide
    2.48
    0
    2.44
    泚
    2.39
    翃
    2.25
    بندی
    2.19
    
    2.17
     behulp
    2.14
    Activations Density 0.001%

    No Known Activations