© 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. 50358
    Prev
    Next
    INDEX
    Explanations

    words following specific tokens

    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
     chiefly
    -0.93
     little
    -0.90
     ↑
    -0.85
    dish
    -0.83
     oras
    -0.81
     towns
    -0.79
    maker
    -0.76
    underbrace
    -0.75
    }_{
    -0.75
    ัส
    -0.75
    POSITIVE LOGITS
     cleric
    0.81
     komplett
    0.76
    ᄐ
    0.76
    这里的
    0.75
    Ott
    0.74
    Рабо
    0.74
     benötigen
    0.74
     аналоги
    0.73
     entire
    0.73
     minimalistic
    0.73
    Activations Density 0.000%

    No Known Activations