© 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. 33747
    Prev
    Next
    INDEX
    Explanations

    multi-inter-cross disciplinary

    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
    дати
    -0.84
    handlung
    -0.79
    τικο
    -0.78
    omorphic
    -0.77
    陝
    -0.76
    upported
    -0.76
     Mérida
    -0.76
     изпъл
    -0.76
     поступ
    -0.76
    ority
    -0.75
    POSITIVE LOGITS
     cross
    2.69
    跨
    2.25
    cross
    2.13
    disciplinary
    2.13
     inter
    2.11
     disciplines
    1.99
    交叉
    1.89
     crossing
    1.80
     crosses
    1.77
     crossover
    1.76
    Activations Density 0.081%

    No Known Activations