© 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. 72972
    Prev
    Next
    INDEX
    Explanations

    performers and scientists

    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
     both
    -1.63
     a
    -1.62
     you
    -1.57
     Both
    -1.52
     length
    -1.31
    书房
    -1.30
     here
    -1.30
     models
    -1.26
    Both
    -1.24
     year
    -1.20
    POSITIVE LOGITS
     největ
    1.38
    vermögen
    1.35
    🐌
    1.33
    anteil
    1.32
    ፒ
    1.31
     YANG
    1.30
    staaten
    1.30
    knüp
    1.28
    öffnung
    1.28
    schrank
    1.27
    Activations Density 0.085%

    No Known Activations