© 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. 22-GEMMASCOPE-RES-131K
    4. 54510
    Prev
    Next
    INDEX
    Explanations

    authenticity and superlatives

    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
     among
    -1.02
    ڼ
    -0.99
     a
    -0.94
    ⌝
    -0.91
     or
    -0.90
    τερα
    -0.88
    liciter
    -0.88
     geçmiş
    -0.86
     an
    -0.84
     ellas
    -0.84
    POSITIVE LOGITS
     most
    1.84
    真正的
    1.65
    真正
    1.65
     realmente
    1.59
     skuto
    1.38
     بیشتر
    1.37
    actually
    1.37
     большин
    1.36
     really
    1.35
     actually
    1.35
    Activations Density 0.053%

    No Known Activations