© 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. 98667
    Prev
    Next
    INDEX
    Explanations

    repair, book, why, game, the, risk

    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
    هرة
    -0.94
     esforço
    -0.91
     silêncio
    -0.80
    Fech
    -0.79
     sogenannten
    -0.78
     getLast
    -0.77
    Reproduced
    -0.77
     sonho
    -0.75
     cumbersome
    -0.75
    车型
    -0.75
    POSITIVE LOGITS
    EFFECT
    0.84
     سبتمبر
    0.83
    вір
    0.83
     solución
    0.82
    kegaard
    0.81
    ՝
    0.81
    今日も
    0.79
    bear
    0.79
     dieß
    0.78
    รับ
    0.77
    Activations Density 0.003%

    No Known Activations