© 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. 69857
    Prev
    Next
    INDEX
    Explanations

    Next steps and attacks

    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
     bekam
    -1.03
    ›
    -0.78
     предыду
    -0.77
     Université
    -0.77
    бир
    -0.76
     storyline
    -0.76
    useum
    -0.75
    litre
    -0.75
     Hwy
    -0.75
     reboot
    -0.75
    POSITIVE LOGITS
    endless
    0.91
    /…
    0.88
     pretty
    0.83
     dica
    0.81
    精英
    0.81
     مراجعه
    0.80
     restri
    0.78
    𝖍
    0.78
    Pretty
    0.77
    Yay
    0.77
    Activations Density 0.001%

    No Known Activations