© 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. 34-GEMMASCOPE-RES-131K
    7. 93011
    Prev
    Next
    INDEX
    Explanations

    deployed systems

    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
    念头
    -0.79
     Leland
    -0.77
    odied
    -0.75
     revamped
    -0.74
    ziału
    -0.72
     climax
    -0.71
    満
    -0.71
     reformed
    -0.71
     GMC
    -0.71
     creada
    -0.69
    POSITIVE LOGITS
     deployment
    5.34
     deployments
    4.47
     deployed
    4.47
     Deployment
    4.25
     deploy
    4.22
    deployment
    4.19
    Deployment
    4.06
    deploy
    4.00
     deploying
    3.92
    Deploy
    3.73
    Activations Density 0.108%

    No Known Activations