© 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. 80905
    Prev
    Next
    INDEX
    Explanations

    research and methodologies

    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
    Belf
    -0.80
    =");
    -0.79
     CERN
    -0.76
     philosophie
    -0.75
    <0xB8>
    -0.75
     brome
    -0.75
     vicente
    -0.74
    EDWARD
    -0.73
    Aws
    -0.73
     educator
    -0.73
    POSITIVE LOGITS
     research
    2.38
    research
    1.88
    Research
    1.87
     Research
    1.82
     RESEARCH
    1.63
    RESEARCH
    1.54
     fieldwork
    1.51
     исследова
    1.48
     researchers
    1.46
     researcher
    1.44
    Activations Density 0.032%

    No Known Activations