© 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. 86701
    Prev
    Next
    INDEX
    Explanations

    technical and mathematical terms

    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
     multicolore
    -1.74
     specifiche
    -1.46
     dilaporkan
    -1.46
     fotografii
    -1.45
     vernis
    -1.45
     ᾿
    -1.44
     太阳
    -1.44
     margiela
    -1.42
     pittores
    -1.42
     applau
    -1.42
    POSITIVE LOGITS
     their
    2.67
     new
    2.03
     like
    1.63
     actions
    1.57
     others
    1.54
     ситуа
    1.45
     time
    1.43
     benefits
    1.43
     Sortiment
    1.42
     social
    1.41
    Activations Density 0.028%

    No Known Activations