© 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. 910
    Prev
    Next
    INDEX
    Explanations

    geometric code structures

    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
    mathrm
    -1.64
    >
    -1.52
     name
    -1.47
    ־ה
    -1.40
    包括
    -1.38
    其中
    -1.37
     ()=>
    -1.35
    “.
    -1.34
    lıkla
    -1.33
     centaines
    -1.30
    POSITIVE LOGITS
    Visión
    1.38
    chränkungen
    1.35
     również
    1.34
     skolan
    1.32
     guerrero
    1.27
     respostas
    1.26
     nestled
    1.23
    Consejos
    1.23
     весьма
    1.21
    Tant
    1.21
    Activations Density 0.042%

    No Known Activations