© 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. 58335
    Prev
    Next
    INDEX
    Explanations

    controller definitions and actions

    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
    [:,:,
    -0.84
    ‬‬
    -0.77
    formatics
    -0.77
     brinquedo
    -0.75
    Få
    -0.74
     even
    -0.74
    èbre
    -0.74
    ᯽
    -0.74
     иллюстрация
    -0.73
    bacher
    -0.71
    POSITIVE LOGITS
     before
    1.28
     перед
    1.16
    before
    1.07
     layout
    0.98
     skip
    0.94
    skip
    0.91
    protect
    0.88
     înainte
    0.87
     around
    0.87
     helper
    0.87
    Activations Density 0.013%

    No Known Activations