© 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. 82593
    Prev
    Next
    INDEX
    Explanations

    exercise machines

    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
     dioces
    -0.86
     GoPro
    -0.81
    SMB
    -0.80
    lierung
    -0.74
    notas
    -0.73
     Fawcett
    -0.72
     Thermostat
    -0.71
    KAS
    -0.71
    Zara
    -0.70
     graphene
    -0.70
    POSITIVE LOGITS
     machines
    2.39
     machine
    2.08
    machines
    1.86
     Machines
    1.82
    machine
    1.70
     máquinas
    1.61
    Machine
    1.54
    Machines
    1.51
     Machine
    1.46
     máquina
    1.33
    Activations Density 0.023%

    No Known Activations