© 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. 9774
    Prev
    Next
    INDEX
    Explanations

    file operations like seek

    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
    ↵
    -1.64
     belated
    -1.41
     ove
    -1.35
     derece
    -1.35
    ;");
    -1.34
     olması
    -1.32
    ㄇ
    -1.26
     этого
    -1.22
    ,",
    -1.21
     таких
    -1.17
    POSITIVE LOGITS
     where
    1.73
    ortic
    1.44
    medriver
    1.43
    ATIVE
    1.37
    работки
    1.32
     defends
    1.31
    かで
    1.31
     estadounid
    1.28
     for
    1.27
     tilby
    1.27
    Activations Density 0.006%

    No Known Activations