© 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. 1335
    Prev
    Next
    INDEX
    Explanations

    Concerned PDP members

    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
     immigration
    -0.76
     vini
    -0.75
     DataTypes
    -0.73
    ICLE
    -0.73
     imperf
    -0.72
     моде
    -0.72
     самому
    -0.72
     сама
    -0.71
     luci
    -0.70
     Aé
    -0.69
    POSITIVE LOGITS
     oil
    1.52
    oil
    1.48
    Oil
    1.36
     Oil
    1.26
     pipeline
    1.25
     pipelines
    1.20
     pipe
    0.99
     mangrove
    0.97
    OIL
    0.96
    Pipeline
    0.94
    Activations Density 0.002%

    No Known Activations