© 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. 42023
    Prev
    Next
    INDEX
    Explanations

    first instance of roles, projects, and events

    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
     they
    -1.64
     you
    -1.63
    はまだ
    -1.55
    THEY
    -1.45
    ܧ
    -1.41
     ugyan
    -1.38
     your
    -1.33
    嵜
    -1.32
    耵
    -1.30
    枚目
    -1.28
    POSITIVE LOGITS
     beiden
    1.38
    我也不
    1.30
    ým
    1.28
    ссор
    1.24
     with
    1.22
    batal
    1.21
     مختلفة
    1.21
    альных
    1.20
     seperti
    1.19
     笑
    1.19
    Activations Density 0.076%

    No Known Activations