© 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. 60751
    Prev
    Next
    INDEX
    Explanations

    Japanese, Russian, English, and Korean 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
    }%
    -0.95
    eamiento
    -0.91
     asociaciones
    -0.91
     называется
    -0.90
     najlepiej
    -0.90
    子さん
    -0.90
     denominado
    -0.86
    上的
    -0.86
     which
    -0.84
     erklär
    -0.84
    POSITIVE LOGITS
     who
    2.42
    が
    1.88
     tarafından
    1.80
    에게
    1.70
     نے
    1.52
     द्वारा
    1.46
     by
    1.38
    가
    1.28
    who
    1.23
    의
    1.20
    Activations Density 0.002%

    No Known Activations