© 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. 65948
    Prev
    Next
    INDEX
    Explanations

    makeshift, WPF, advices

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

    The neuron tends to fire on relatively uncommon, content-bearing words (proper names, technical terms, or distinctive adjectives) rather than on common function 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
    pecabe
    -3.14
    
    -3.02
    OUTUBE
    -2.81
    ⽼
    -2.70
     求人
    -2.70
    亖
    -2.67
    ⃚
    -2.66
    ープン
    -2.66
    ⼥
    -2.59
     墊
    -2.58
    POSITIVE LOGITS
    在他的
    2.34
    し
    2.25
    様の
    2.23
    出来る
    2.20
     scientist
    2.16
    但她
    2.16
    5
    2.14
     وأ
    2.14
     
    2.14
    ation
    2.13
    Activations Density 0.012%

    No Known Activations