© 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. 42281
    Prev
    Next
    INDEX
    Explanations

    shared activities and experiences

    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
    ↵
    -1.34
     is
    -1.16
     todos
    -1.10
    '
    -1.10
     has
    -1.09
     in
    -1.09
     cada
    -1.07
     todas
    -1.07
     nachdem
    -1.06
     jiwa
    -1.05
    POSITIVE LOGITS
    笵
    1.40
    čku
    1.34
     Israël
    1.25
    และ
    1.23
     osoba
    1.22
     kokos
    1.16
     igra
    1.16
     zima
    1.16
     compagn
    1.15
     biele
    1.15
    Activations Density 0.046%

    No Known Activations