© 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. 1691
    Prev
    Next
    INDEX
    Explanations

    actors and character names

    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
    See
    -1.45
     kaarangay
    -1.38
     humaine
    -1.35
     bort
    -1.30
     飾
    -1.24
     inny
    -1.23
    certain
    -1.22
     confronti
    -1.21
        
    -1.20
     bottes
    -1.20
    POSITIVE LOGITS
     whom
    1.21
    𝙸
    1.15
     :
    1.13
     unleashed
    1.12
     synerg
    1.11
    Synchronization
    1.11
     législation
    1.10
    surname
    1.09
    مدیر
    1.09
     facili
    1.09
    Activations Density 0.614%

    No Known Activations