© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45149
    Prev
    Next
    INDEX
    Explanations

    peanut butter, Nutella, Oreo

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

    The neuron is highly activated by occurrences of the phrase “peanut butter” (including headings or repeated mentions of peanut butter).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    0
    -2.03
    ࿊
    -2.03
     oi
    -2.02
     it
    -1.93
    â
    -1.91
    ;-
    -1.80
     новая
    -1.75
     dotyczące
    -1.74
    各样的
    -1.74
     I
    -1.73
    POSITIVE LOGITS
     Only
    2.02
     successivamente
    1.94
     Before
    1.88
    　　「
    1.84
     esclusivamente
    1.76
     dallo
    1.75
    Only
    1.75
    月末
    1.74
     obeying
    1.73
     粉色
    1.69
    Activations Density 0.006%

    No Known Activations