© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108183
    Prev
    Next
    INDEX
    Explanations

    commercial licenses

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

    The neuron fires on price‐and‐purchase contexts, especially numbers, discounts, percentages, and purchase‐related 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
     free
    -3.56
    free
    -2.95
     Free
    -2.50
    Free
    -2.50
     FREE
    -2.41
     беспла
    -2.34
    免费
    -2.25
    FREE
    -2.17
    無料
    -2.08
    免費
    -1.93
    POSITIVE LOGITS
     licenses
    1.36
     lifetime
    1.25
     license
    1.16
    licenses
    1.11
     bundle
    1.09
     licences
    1.09
    lifetime
    1.06
     Lifetime
    1.00
     access
    0.95
    Lifetime
    0.95
    Activations Density 0.061%

    No Known Activations