© 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. 124033
    Prev
    Next
    INDEX
    Explanations

    twitter, imgur, ubuntu, sports

    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
     "
    -2.22
    ?"
    -2.13
    ),"
    -2.05
     in
    -2.03
     by
    -2.00
    🧌
    -1.92
    ]."
    -1.90
     '
    -1.82
     has
    -1.81
    "?
    -1.80
    POSITIVE LOGITS
    .
    1.98
     aktuelle
    1.90
     tht
    1.82
     吳
    1.81
    禵
    1.77
     komplette
    1.76
    褡
    1.72
     ursprüng
    1.70
     vorhand
    1.70
     kostenlose
    1.69
    Activations Density 0.001%

    No Known Activations