© 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. 22-GEMMASCOPE-RES-131K
    7. 75369
    Prev
    Next
    INDEX
    Explanations

    food ingredients and instructions

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

    The neuron strongly activates on numeric quantities and measurements (e.g. ingredient amounts) in recipe ingredient lists.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     this
    -1.19
     their
    -1.18
     كندا
    -1.11
     baskılı
    -1.11
     these
    -1.09
     accett
    -1.07
     those
    -1.06
    xfe
    -1.02
     respetu
    -1.01
     Einführung
    -0.97
    POSITIVE LOGITS
     سینم
    1.17
     presa
    1.13
     monté
    1.13
     veste
    1.08
     notori
    1.06
    あなた
    1.04
    omio
    1.03
     MotionEvent
    1.02
    arrhea
    1.00
     linf
    1.00
    Activations Density 0.010%

    No Known Activations