© 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. 34785
    Prev
    Next
    INDEX
    Explanations

    conjugate

    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
    _{+}
    -0.76
    卒
    -0.76
    Competi
    -0.73
     crackers
    -0.71
     Growers
    -0.71
    ਂ
    -0.69
    izawa
    -0.68
    tokio
    -0.68
     Competition
    -0.68
    underground
    -0.67
    POSITIVE LOGITS
     conjugate
    5.31
    conjug
    5.03
     Conjug
    4.88
    Conjug
    4.78
     conjug
    4.69
     conjugated
    4.44
     conjugation
    4.31
    conjugated
    3.75
     conj
    3.05
    conj
    2.94
    Activations Density 0.141%

    No Known Activations