© 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. 34-GEMMASCOPE-RES-131K
    7. 83809
    Prev
    Next
    INDEX
    Explanations

    register select and control

    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
     tecnico
    -0.84
     難
    -0.82
     tecnici
    -0.82
     destacar
    -0.81
    uchsia
    -0.81
     розви
    -0.79
     Ngày
    -0.79
    conector
    -0.77
     substantially
    -0.76
     вагі
    -0.76
    POSITIVE LOGITS
    select
    1.19
    Select
    1.07
    register
    1.07
     select
    1.06
     register
    1.01
    Register
    0.99
     Register
    0.95
     Select
    0.94
     fiables
    0.94
     fó
    0.92
    Activations Density 0.031%

    No Known Activations