© 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. 98686
    Prev
    Next
    INDEX
    Explanations

    micelles and surfactants

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

    scientific terms related to micelles and molecular structures.

    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
    ansu
    -0.71
     مصرى
    -0.71
    绝
    -0.70
    象
    -0.69
     Mazda
    -0.69
    koku
    -0.68
    文分享
    -0.67
     секре
    -0.67
     workstations
    -0.67
     Dear
    -0.66
    POSITIVE LOGITS
     mic
    2.30
    mic
    1.59
     Mic
    1.41
    Mic
    1.27
     mics
    1.20
     microphone
    1.20
     aggregates
    1.07
     aggregation
    1.06
     solub
    1.00
     soap
    0.99
    Activations Density 0.148%

    No Known Activations