© 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. 2157
    Prev
    Next
    INDEX
    Explanations

    search and comparison

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

    The neuron fires strongly for mentions of price‐comparison websites or similar online price‐comparison 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
     Markham
    -0.81
    typeorm
    -0.79
    ով
    -0.77
    cotti
    -0.77
    aturas
    -0.76
    puede
    -0.76
    marle
    -0.75
    mongodb
    -0.75
     Spectra
    -0.74
    providedIn
    -0.74
    POSITIVE LOGITS
     search
    1.84
     comparison
    1.73
     aggreg
    1.66
     compare
    1.45
     meta
    1.38
     price
    1.38
     comparisons
    1.38
    compare
    1.30
     Comparison
    1.27
    comparison
    1.27
    Activations Density 0.072%

    No Known Activations