© 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. 69408
    Prev
    Next
    INDEX
    Explanations

    intense states or qualities

    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
    錘
    -1.33
    :
    -1.33
     Füßen
    -1.32
     другим
    -1.27
     других
    -1.24
     italianos
    -1.24
     نگهد
    -1.23
    緞
    -1.23
     in
    -1.23
    Ita
    -1.22
    POSITIVE LOGITS
     and
    2.22
    蚡
    1.64
     墊
    1.62
     because
    1.49
     pios
    1.44
    aktery
    1.42
     イラストレーション
    1.42
    🖖
    1.41
     restaurante
    1.40
    鱨
    1.40
    Activations Density 0.043%

    No Known Activations