© 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. 896
    Prev
    Next
    INDEX
    Explanations

    system components

    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
    keteers
    -1.35
     advice
    -1.23
    Ⅵ
    -1.21
    формация
    -1.20
     for
    -1.20
    aneers
    -1.20
    zação
    -1.19
     on
    -1.18
     motif
    -1.17
    izzling
    -1.17
    POSITIVE LOGITS
     that
    1.97
     которые
    1.43
     nếu
    1.38
     these
    1.34
    這些
    1.27
     who
    1.26
     если
    1.25
    翆
    1.23
     which
    1.21
    !’
    1.21
    Activations Density 0.131%

    No Known Activations