© 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. 85025
    Prev
    Next
    INDEX
    Explanations

    how to phrase questions

    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
     also
    -1.73
    Dobrý
    -1.45
    Jika
    -1.45
     tomba
    -1.42
     veste
    -1.41
     dacă
    -1.41
     vostre
    -1.40
     jokingly
    -1.39
     Ewig
    -1.38
     Beſ
    -1.37
    POSITIVE LOGITS
     such
    1.59
     столь
    1.58
     takim
    1.49
     dwa
    1.35
     heutige
    1.34
     takimi
    1.28
     зовут
    1.27
     autory
    1.26
     ссылка
    1.25
    极为
    1.24
    Activations Density 0.036%

    No Known Activations