© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49414
    Prev
    Next
    INDEX
    Explanations

    javascript code structure

    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
     Zika
    -1.24
     Snapchat
    -1.20
     emojis
    -1.18
     millennials
    -1.17
     selfie
    -1.10
     selfies
    -1.05
     emoji
    -0.96
     Whatsapp
    -0.94
    @[+][
    -0.88
     Brexit
    -0.88
    POSITIVE LOGITS
     pandemic
    0.92
     Abingdon
    0.82
    jScrollPane
    0.78
    ござ
    0.77
    ాని
    0.77
     Pandemic
    0.75
     brings
    0.75
    Pande
    0.73
     cold
    0.73
     Satoshi
    0.72
    Activations Density 0.136%

    No Known Activations