© 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. 50427
    Prev
    Next
    INDEX
    Explanations

    bits and diseases

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical notation and symbols in technical computing contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Rückseite
    -0.85
    każ
    -0.81
     julio
    -0.81
     письмо
    -0.77
     олив
    -0.77
    抹茶
    -0.77
     kämp
    -0.75
    ırlar
    -0.74
    HON
    -0.74
    iedenis
    -0.74
    POSITIVE LOGITS
     blinded
    1.08
     secret
    1.08
     message
    1.04
     blinding
    1.02
     messages
    1.00
     challenge
    0.96
     commitment
    0.92
     Syndrome
    0.91
     syndrome
    0.91
     Challenge
    0.90
    Activations Density 0.043%

    No Known Activations