© 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. 445
    Prev
    Next
    INDEX
    Explanations

    nut and nuts compounds

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

    The neuron recognizes words related to "nut" including nutshell, Nuttall, nutrients, and nuts in various contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     samh
    -0.83
    izar
    -0.75
     voy
    -0.75
    饉
    -0.75
    chl
    -0.74
    Cont
    -0.73
    illoin
    -0.72
    驻
    -0.72
    survival
    -0.72
     inconsistency
    -0.71
    POSITIVE LOGITS
     Nut
    1.28
    Nut
    1.10
     nut
    1.07
    meg
    0.99
     NUT
    0.95
    case
    0.94
    🥜
    0.91
     Nutt
    0.91
    аз
    0.90
    ープル
    0.88
    Activations Density 0.013%

    No Known Activations