© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118702
    Prev
    Next
    INDEX
    Explanations

    oil and grease

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    osti
    -0.77
    floxacin
    -0.74
    aussian
    -0.73
     email
    -0.72
     a
    -0.71
     dlg
    -0.71
     vě
    -0.69
    degna
    -0.68
     交
    -0.67
    淮
    -0.67
    POSITIVE LOGITS
    OIL
    1.03
    oil
    0.98
    Oil
    0.97
     lubrication
    0.94
    cloth
    0.93
    油
    0.91
     triglycer
    0.91
     OIL
    0.89
     greasy
    0.88
     slick
    0.87
    Activations Density 0.026%

    No Known Activations