© 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. 22-GEMMASCOPE-RES-131K
    4. 68920
    Prev
    Next
    INDEX
    Explanations

    sequences of steps

    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_22/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
    ?』
    -1.21
    ätigung
    -1.07
     weshalb
    -1.05
    水彩
    -1.01
     лише
    -1.01
    Also
    -0.98
    Вопрос
    -0.96
    actéristiques
    -0.95
    Поэтому
    -0.94
     kapas
    -0.94
    POSITIVE LOGITS
     then
    2.31
     затем
    1.34
    then
    1.27
     kemudian
    1.21
     Then
    1.20
     wtedy
    1.20
     Luego
    1.18
     thereafter
    1.16
    然后
    1.14
     vervolgens
    1.11
    Activations Density 0.100%

    No Known Activations