© 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. 22-GEMMASCOPE-RES-131K
    7. 35822
    Prev
    Next
    INDEX
    Explanations

    research study findings

    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_22/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
     will
    -1.36
    👋
    -1.27
    嫌疑
    -1.20
    ׇ
    -1.18
    ὸν
    -1.09
    KTM
    -1.08
     still
    -1.08
     novelas
    -1.07
    ❣
    -1.07
    🤓
    -1.06
    POSITIVE LOGITS
     study
    1.75
    ֶּ
    1.28
     research
    1.19
     estudo
    1.15
     бампер
    1.13
     ję
    1.13
     Study
    1.13
     estud
    1.13
    cellor
    1.12
     utafiti
    1.12
    Activations Density 0.100%

    No Known Activations