© 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. 85518
    Prev
    Next
    INDEX
    Explanations

    oils and diesel

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

    words related to oils, especially vegetable oils, biodiesel, and plant-derived fats.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects mentions of plant‐derived oils and related oilseed/biodiesel feedstocks.

    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
    ers
    -1.58
    ୌ
    -1.55
     ſel
    -1.52
    ༵
    -1.49
    in
    -1.46
    咴
    -1.43
    项目的
    -1.42
    ong
    -1.42
     金色
    -1.42
    ('''
    -1.41
    POSITIVE LOGITS
     When
    1.59
     were
    1.48
     одним
    1.38
     Если
    1.34
     عندما
    1.33
     Unfortunately
    1.31
    i
    1.30
     Когда
    1.30
     Ursprung
    1.30
     is
    1.29
    Activations Density 0.030%

    No Known Activations