© 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. 3849
    Prev
    Next
    INDEX
    Explanations

    cheaper

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

    The neuron activates on comparative cost terms, especially the word “cheaper” (and similar lower‐price comparisons).

    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
     brainstorm
    -2.20
     cobre
    -1.97
    慌
    -1.95
    要在
    -1.95
    ᡳ
    -1.94
    “
    -1.93
     idén
    -1.92
    𓐍
    -1.91
    今夜
    -1.91
    球迷
    -1.88
    POSITIVE LOGITS
    0
    2.80
    if
    2.28
    ль
    2.09
    饪
    2.06
     uses
    2.05
    もありますが
    1.92
    踯
    1.86
     she
    1.84
    簷
    1.80
    ᠂
    1.80
    Activations Density 0.006%

    No Known Activations