© 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. 34-GEMMASCOPE-RES-131K
    4. 107703
    Prev
    Next
    INDEX
    Explanations

    dreams and cognition

    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_34/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
    Pato
    -0.81
    互动
    -0.77
    𝙪
    -0.76
    Stay
    -0.76
    Anthropo
    -0.75
     aro
    -0.74
    ULO
    -0.73
    aroni
    -0.73
    Elke
    -0.73
     定义
    -0.73
    POSITIVE LOGITS
     your
    1.27
     you
    1.12
     may
    0.95
     Vortrag
    0.92
    perhaps
    0.90
     gavetas
    0.89
     quizá
    0.88
     feelings
    0.87
    lccccc
    0.86
    Oacute
    0.86
    Activations Density 0.000%

    No Known Activations