© 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. 34-GEMMASCOPE-RES-131K
    7. 98033
    Prev
    Next
    INDEX
    Explanations

    low cost, low quality

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

    The neuron is highly sensitive to words signaling low cost or poor quality (notably “cheap” and similar terms).

    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
     undisturbed
    -0.91
    Forma
    -0.90
     unaffected
    -0.89
     spotless
    -0.89
     clean
    -0.89
     ส์
    -0.85
    Clean
    -0.84
    clean
    -0.84
    invoices
    -0.83
    を持つ
    -0.82
    POSITIVE LOGITS
     cheap
    3.53
    cheap
    2.78
     cheaper
    2.58
     inexpensive
    2.50
     cheaply
    2.45
    Cheap
    2.39
     Cheap
    2.38
     cheapest
    2.31
     деше
    2.22
     ارزان
    1.84
    Activations Density 0.064%

    No Known Activations