© 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. 127459
    Prev
    Next
    INDEX
    Explanations

    German quotes and mathematical notations

    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
     also
    -1.27
    ：“……”
    -1.15
     first
    -1.13
     It
    -1.13
    ：……
    -1.12
     jao
    -1.10
    …»
    -1.07
     宣传
    -1.03
    ворот
    -1.02
     aasta
    -1.02
    POSITIVE LOGITS
     pranzo
    1.27
     to
    1.24
    导致
    1.18
    even
    1.16
    INSEE
    1.14
    čio
    1.13
    ísica
    1.08
    reter
    1.07
     stali
    1.05
    ']")
    1.05
    Activations Density 0.227%

    No Known Activations