© 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. 98158
    Prev
    Next
    INDEX
    Explanations

    initial suffixes

    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
     earlier
    -0.97
    勦
    -0.93
     schwed
    -0.93
    事前に
    -0.92
    landse
    -0.91
     WI
    -0.88
    ih
    -0.86
     früher
    -0.85
    有可能
    -0.80
    {
    -0.79
    POSITIVE LOGITS
    izers
    1.63
    isation
    1.62
    izations
    1.34
    izing
    1.29
    iser
    1.23
    iseur
    1.20
    ising
    1.15
    isers
    1.11
    izes
    1.07
    isms
    1.06
    Activations Density 0.012%

    No Known Activations