© 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. 10-GEMMASCOPE-RES-131K
    7. 104049
    Prev
    Next
    INDEX
    Explanations

    code libraries and projects

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

    dots in package names, namespaces, or domain identifiers in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     santuario
    -2.05
    figurine
    -1.80
    groet
    -1.72
    gilet
    -1.70
     they
    -1.63
     gemaakt
    -1.63
    aktionen
    -1.62
     beira
    -1.57
     maría
    -1.56
     monumento
    -1.56
    POSITIVE LOGITS
     but
    1.92
     Even
    1.91
    Even
    1.84
     -
    1.82
                    
    1.82
     But
    1.81
    </strong>
    1.75
    Still
    1.71
              
    1.66
    </i>
    1.66
    Activations Density 0.000%

    No Known Activations