© 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. 40768
    Prev
    Next
    INDEX
    Explanations

    api and build keywords

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

    The neuron activates on occurrences of the substring “api” in code—especially in module‐import or require paths.

    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
    BeginContext
    -1.19
    nikon
    -1.18
    Odour
    -1.17
     inmigrantes
    -1.15
    又是一
    -1.14
    ție
    -1.13
     компании
    -1.12
     primeiro
    -1.12
    saturday
    -1.09
    ሾ
    -1.09
    POSITIVE LOGITS
     for
    1.48
     even
    1.28
     delicioso
    1.23
     any
    1.20
     MONTE
    1.20
    جون
    1.19
     ALPH
    1.16
     when
    1.15
     hoeveel
    1.11
    นี้
    1.10
    Activations Density 0.031%

    No Known Activations