© 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. 85130
    Prev
    Next
    INDEX
    Explanations

    primitive types and operations

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

    The neuron fires on occurrences of the word “primitive,” marking mentions of primitive types.

    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
    幛
    -2.80
    𓆜
    -2.55
    羮
    -2.50
    ༷
    -2.48
    变成了
    -2.45
    й
    -2.42
    奩
    -2.38
    ꜆
    -2.34
     Diſ
    -2.28
    宬
    -2.28
    POSITIVE LOGITS
     After
    3.41
     Importantly
    3.33
     Although
    3.27
     Despite
    3.27
     Ultimately
    3.25
     Interestingly
    3.22
     Undoubtedly
    3.22
     Consequently
    3.20
     Depending
    3.20
     Because
    3.19
    Activations Density 0.004%

    No Known Activations