© 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. 2402
    Prev
    Next
    INDEX
    Explanations

    in followed by abstract concepts

    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
     particulière
    -0.94
     Zustimmung
    -0.94
    чого
    -0.93
     miesto
    -0.84
     поводу
    -0.83
    enlace
    -0.81
     kitabı
    -0.80
    般
    -0.79
     cuối
    -0.79
    덟
    -0.79
    POSITIVE LOGITS
     theory
    1.99
     name
    1.99
     reality
    1.94
     practice
    1.83
    name
    1.70
     actuality
    1.66
     spirit
    1.60
     essence
    1.48
     principle
    1.47
    theory
    1.46
    Activations Density 0.068%

    No Known Activations