© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98395
    Prev
    Next
    INDEX
    Explanations

    make up a group or percentage

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

    The neuron detects occurrences of the phrase “make up,” especially when used in numeric or percentage contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Externe
    -0.75
     bunch
    -0.75
     sebaliknya
    -0.74
    եր
    -0.73
     inconnu
    -0.72
     Commencez
    -0.71
     nara
    -0.70
    NIA
    -0.69
    <!--<
    -0.69
    endipity
    -0.68
    POSITIVE LOGITS
     up
    2.59
     make
    1.84
    make
    1.70
     MAKE
    1.55
    Make
    1.50
    makes
    1.45
     Make
    1.42
    MAKE
    1.40
    Makes
    1.38
     makeup
    1.38
    Activations Density 0.022%

    No Known Activations