© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73862
    Prev
    Next
    INDEX
    Explanations

    maximum likelihood estimation

    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
    _
    -1.47
     strongest
    -1.37
     weakest
    -1.34
    -1.30
     which
    -1.27
     可以
    -1.27
     três
    -1.27
    ad
    -1.23
     caratteristiche
    -1.23
    的问道
    -1.19
    POSITIVE LOGITS
     Leur
    1.36
    cím
    1.35
     Institu
    1.35
    .
    1.33
     udaler
    1.30
    fiable
    1.29
    capacete
    1.28
    Toeschouwers
    1.27
    vetrain
    1.27
    THING
    1.27
    Activations Density 0.033%

    No Known Activations