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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91466
    Prev
    Next
    INDEX
    Explanations

    academic disciplines and subjects

    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
    нял
    -0.72
    chema
    -0.70
    œurs
    -0.70
     chuyến
    -0.69
     Mario
    -0.68
    Radiant
    -0.68
    얕
    -0.67
    ผิว
    -0.67
     Мари
    -0.67
    ੂੰ
    -0.67
    POSITIVE LOGITS
     disciplines
    1.01
     discipline
    0.94
     дисципли
    0.85
     Discipline
    0.83
    ContentAsync
    0.82
     disciplinas
    0.81
    disciplinary
    0.78
    ∎
    0.75
     disciplina
    0.74
     дисци
    0.74
    Activations Density 0.018%

    No Known Activations