© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20223
    Prev
    Next
    INDEX
    Explanations

    assembly instructions

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

    The neuron is detecting the “ifeq” conditional directive (the Makefile “ifeq(…)” test).

    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
     because
    -1.66
     any
    -1.55
     both
    -1.48
    But
    -1.44
     Both
    -1.37
    ↵
    -1.34
    쾰
    -1.32
     before
    -1.30
     زیرا
    -1.24
     but
    -1.23
    POSITIVE LOGITS
    可以
    1.38
    ⎚
    1.35
     pilares
    1.35
    Beschrijving
    1.34
     استناد
    1.33
    閪
    1.30
    subsubsection
    1.27
     sommet
    1.27
     diſt
    1.26
    下雨
    1.26
    Activations Density 0.001%

    No Known Activations