© 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. 71688
    Prev
    Next
    INDEX
    Explanations

    variables and covariates

    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
     »)
    -1.56
     که
    -1.52
     eren
    -1.33
    nisses
    -1.32
    '")
    -1.32
    茕
    -1.30
     не
    -1.29
    erweise
    -1.28
     prata
    -1.28
     terjadi
    -1.28
    POSITIVE LOGITS
     Dijo
    1.42
    嚳
    1.41
     Coloque
    1.41
     such
    1.39
     unveil
    1.33
     THOSE
    1.31
     then
    1.29
     Lleva
    1.27
     peo
    1.26
    ござい
    1.26
    Activations Density 0.091%

    No Known Activations