© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39036
    Prev
    Next
    INDEX
    Explanations

    env gene

    np_acts-logits-general · gemini-2.5-flash-lite

    technical or scientific terms and acronyms, particularly those found in biology, chemistry, and computer science.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    <td>
    -1.64
           
    -1.64
         
    -1.59
    人たち
    -1.54
    .’
    -1.52
                   
    -1.46
            
    -1.46
     Those
    -1.43
              
    -1.42
     vorliegenden
    -1.42
    POSITIVE LOGITS
     of
    2.19
    handelt
    1.72
    蒟
    1.52
     peo
    1.48
     intrigu
    1.48
     EINVAL
    1.48
    χο
    1.47
    。"
    1.45
    mlink
    1.41
     ſol
    1.40
    Activations Density 0.038%

    No Known Activations