© 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. 80643
    Prev
    Next
    INDEX
    Explanations

    came across / stumbled upon

    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
    来
    -1.43
     actuellement
    -1.23
    i
    -1.17
     this
    -1.16
    2
    -1.14
    取
    -1.14
     each
    -1.13
     now
    -1.12
    和
    -1.11
    ila
    -1.10
    POSITIVE LOGITS
     in
    1.62
     måde
    1.52
    atás
    1.50
    PUESTA
    1.42
    𝕻
    1.37
     atendido
    1.34
    他们在
    1.34
     Ně
    1.34
    罴
    1.34
     interessantes
    1.33
    Activations Density 0.090%

    No Known Activations