© 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. 109641
    Prev
    Next
    INDEX
    Explanations

    music and pop culture references

    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
     protections
    -0.86
     cotone
    -0.86
    arande
    -0.82
    づくり
    -0.81
     vescovo
    -0.79
     distributes
    -0.78
    真的是
    -0.77
    vapor
    -0.75
     reput
    -0.75
    信任
    -0.75
    POSITIVE LOGITS
    🤘
    1.16
    🤟
    0.96
     Osbourne
    0.91
    🎅
    0.90
     "'
    0.89
    Ů
    0.88
     Artisan
    0.85
    ια
    0.84
    setz
    0.82
    ="@+
    0.81
    Activations Density 0.043%

    No Known Activations