© 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. 87003
    Prev
    Next
    INDEX
    Explanations

    remainder when divided

    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
     Munster
    -0.78
    μένες
    -0.75
     statistique
    -0.74
    áját
    -0.71
    Volume
    -0.70
     össze
    -0.69
     summation
    -0.69
    ensis
    -0.69
    owników
    -0.69
    Sum
    -0.69
    POSITIVE LOGITS
     remainder
    2.88
    remainder
    2.11
     residue
    2.02
     Rema
    2.02
     оста
    1.95
    Rema
    1.93
    余
    1.88
     rema
    1.80
     leftover
    1.78
     leftovers
    1.70
    Activations Density 0.107%

    No Known Activations