© 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. 102834
    Prev
    Next
    INDEX
    Explanations

    luggage and baggage storage

    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_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
     "];
    -1.48
    lamabad
    -1.46
    樯
    -1.44
    ___________
    -1.39
    呲
    -1.36
     знал
    -1.33
    Om
    -1.30
     ſever
    -1.27
                        
    -1.24
     exemplu
    -1.23
    POSITIVE LOGITS
     is
    1.55
     luggage
    1.53
    傀
    1.40
     cuando
    1.38
    adaran
    1.28
     όταν
    1.27
    dbury
    1.27
    匍
    1.26
     Luggage
    1.25
     було
    1.24
    Activations Density 0.029%

    No Known Activations