© 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. 104235
    Prev
    Next
    INDEX
    Explanations

    quoted text and dialogues

    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
     andre
    -1.48
     astounding
    -1.48
     și
    -1.43
    
    -1.41
     arid
    -1.37
     insanely
    -1.33
     famed
    -1.32
     acclaimed
    -1.30
    ᨆ
    -1.29
     và
    -1.27
    POSITIVE LOGITS
     There
    1.34
     with
    1.32
    …?
    1.26
     :\\
    1.21
     from
    1.16
    There
    1.12
     kerjasama
    1.12
     например
    1.11
     sebagainya
    1.11
     “…
    1.09
    Activations Density 1.114%

    No Known Activations