© 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. 3912
    Prev
    Next
    INDEX
    Explanations

    technique error :

    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
    螃
    -1.52
     oamen
    -1.36
     parfüm
    -1.34
     ibland
    -1.29
     abiye
    -1.27
    fertig
    -1.27
     dava
    -1.26
    шев
    -1.24
     beslu
    -1.24
     huset
    -1.23
    POSITIVE LOGITS
     ebenfalls
    1.54
     is
    1.38
    ,
    1.30
     )
    1.27
     نیز
    1.24
    ㅈ
    1.23
     invece
    1.22
     similarly
    1.20
     chiaramente
    1.15
    :
    1.13
    Activations Density 0.118%

    No Known Activations