© 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. 34-GEMMASCOPE-RES-131K
    7. 82728
    Prev
    Next
    INDEX
    Explanations

    complexity and diversity

    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
    の高い
    -1.05
     velmi
    -0.97
     bardzo
    -0.92
     매우
    -0.87
     ļoti
    -0.87
     exceptionally
    -0.85
    Extremely
    -0.85
    VIRONMENT
    -0.85
     difficiles
    -0.84
     extrêmement
    -0.84
    POSITIVE LOGITS
     simplicity
    1.38
     complexity
    1.35
    siveness
    1.29
     difficulty
    1.29
     novelty
    1.23
    ความ
    1.22
    tiveness
    1.21
     strength
    1.20
     effectiveness
    1.20
     heav
    1.19
    Activations Density 0.178%

    No Known Activations