© 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. 10-GEMMASCOPE-RES-131K
    7. 20426
    Prev
    Next
    INDEX
    Explanations

    rare occurrences

    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_10/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
     bekämp
    -1.62
     ήταν
    -1.60
     idén
    -1.42
    memories
    -1.31
    vedades
    -1.29
     млрд
    -1.27
     privés
    -1.27
    ING
    -1.27
     bereits
    -1.26
     normales
    -1.25
    POSITIVE LOGITS
     rare
    1.74
     rarely
    1.71
     few
    1.52
     when
    1.46
     know
    1.45
     Rare
    1.43
     seldom
    1.41
     even
    1.38
     unheard
    1.34
    稀
    1.32
    Activations Density 0.034%

    No Known Activations