© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33190
    Prev
    Next
    INDEX
    Explanations

    petrochemicals and petroleum products

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

    words related to petroleum and petrochemicals.

    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
     animali
    -0.74
    эн
    -0.73
     flocks
    -0.72
    Dopo
    -0.72
    npos
    -0.71
    loc
    -0.70
     widowed
    -0.69
    chs
    -0.69
     behöver
    -0.68
     nė
    -0.68
    POSITIVE LOGITS
    atum
    0.96
    lagten
    0.94
    paedia
    0.82
     Explain
    0.81
     triunfo
    0.79
     ТА
    0.78
     thùng
    0.77
    ungere
    0.75
     上午
    0.75
     Tao
    0.75
    Activations Density 0.022%

    No Known Activations