© 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. 22-GEMMASCOPE-RES-131K
    7. 36222
    Prev
    Next
    INDEX
    Explanations

    cheap items and services

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

    This neuron responds strongly to the adjective “cheap.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     they
    -2.63
    
    -2.23
    ?”
    -2.19
     hapless
    -2.13
     “
    -2.11
    ௅
    -2.06
    バレンタイン
    -2.06
    
    -2.03
    ческих
    -2.02
    GEBUR
    -2.02
    POSITIVE LOGITS
    0
    3.02
    2
    2.77
    4
    2.48
    6
    2.44
    ER
    2.39
    ﮨ
    2.34
    饪
    2.31
    自己的
    2.28
    9
    2.28
    .
    2.20
    Activations Density 0.011%

    No Known Activations