© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12678
    Prev
    Next
    INDEX
    Explanations

    cheap, inexpensive, low cost

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

    The main thing this neuron does is detect mentions of flavoring or added ingredients in food and beverage contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    禅
    0.64
     exquisite
    0.63
    优雅
    0.61
     exclusivos
    0.61
     exclusive
    0.60
     தனி
    0.59
    exclusive
    0.59
     exclusivity
    0.58
     exquisitely
    0.58
    🗼
    0.57
    POSITIVE LOGITS
     cheap
    2.39
    cheap
    2.17
     inexpensive
    2.14
     деше
    2.08
    Cheap
    2.06
     Cheap
    2.02
     cheaply
    1.96
     cheaper
    1.95
     cheapest
    1.88
     rẻ
    1.73
    Activations Density 0.862%

    No Known Activations