© 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. 89974
    Prev
    Next
    INDEX
    Explanations

    aloe vera

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

    references to aloe vera and its properties.

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

    The neuron strongly activates on mentions of “aloe vera” (especially in product or juice contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     leite
    -0.76
     ???
    -0.76
    deau
    -0.74
     negra
    -0.71
     deles
    -0.70
     hormone
    -0.69
     rice
    -0.69
     iron
    -0.66
     peanut
    -0.65
     Reiss
    -0.65
    POSITIVE LOGITS
     aloe
    1.94
     Aloe
    1.83
    Aloe
    1.60
    aloe
    1.35
     soothing
    1.24
     alo
    1.20
     ALO
    1.18
     Alo
    1.12
     soothe
    1.10
     vera
    1.05
    Activations Density 0.015%

    No Known Activations