© 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. 110962
    Prev
    Next
    INDEX
    Explanations

    specific words followed by context

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

    The neuron consistently lights up on product‐oriented, promotional descriptions—i.e. marketing or advertising copy.

    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
     спеціаль
    -1.01
    nutie
    -0.91
     όταν
    -0.91
     yyb
    -0.89
     dámské
    -0.85
    鰈
    -0.84
    觀眾
    -0.83
    Comparator
    -0.82
    鏷
    -0.82
    ּוֹ
    -0.81
    POSITIVE LOGITS
     original
    1.05
     Provence
    1.01
     harmon
    0.96
     romantic
    0.90
     молоде
    0.89
     сти
    0.88
     will
    0.82
     OPTIONS
    0.82
     siker
    0.81
     diversi
    0.81
    Activations Density 0.008%

    No Known Activations