© 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. 22-GEMMASCOPE-RES-131K
    7. 98249
    Prev
    Next
    INDEX
    Explanations

    seeds received

    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_22/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
     penelitian
    -0.85
     nesten
    -0.84
    וּ
    -0.82
    uance
    -0.81
     приготовить
    -0.80
     envies
    -0.80
     rekomendasi
    -0.79
    柃
    -0.78
     propria
    -0.78
     получить
    -0.78
    POSITIVE LOGITS
    もあって
    1.00
     Duties
    0.91
     mám
    0.88
    boretum
    0.88
     paño
    0.86
    Assess
    0.84
     detaylı
    0.84
    佝
    0.84
     využí
    0.84
    際に
    0.84
    Activations Density 0.022%

    No Known Activations