© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99744
    Prev
    Next
    INDEX
    Explanations

    names and locations

    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
     here
    -1.58
     diffic
    -1.27
     poderão
    -1.21
    chito
    -1.20
    訁
    -1.19
     哪些
    -1.16
     собрать
    -1.16
     cantora
    -1.16
     Then
    -1.15
    了很多
    -1.15
    POSITIVE LOGITS
    ",
    1.70
    ミ
    1.41
    corazón
    1.38
     goles
    1.34
     yaprak
    1.33
     wę
    1.33
    .",
    1.33
     bonté
    1.32
     nasze
    1.32
     debe
    1.32
    Activations Density 0.020%

    No Known Activations