© 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. 82484
    Prev
    Next
    INDEX
    Explanations

    children's books or phrases

    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
    İŞ
    -0.86
    kovou
    -0.81
    樣子
    -0.80
    getStringExtra
    -0.77
     дописа
    -0.77
     Зна
    -0.76
    неопр
    -0.75
    ҵ
    -0.75
     Söz
    -0.75
    тических
    -0.75
    POSITIVE LOGITS
     child
    1.06
     Child
    0.82
     trotz
    0.77
    ,:
    0.73
    噪音
    0.73
     mandiri
    0.73
    >?
    0.72
    卜
    0.71
    avro
    0.71
     rich
    0.71
    Activations Density 0.032%

    No Known Activations