© 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. 116679
    Prev
    Next
    INDEX
    Explanations

    either version 2

    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
    eſt
    -0.84
    depends
    -0.81
     bezpiecz
    -0.81
     jepang
    -0.81
    binding
    -0.81
     Teléfono
    -0.80
     différentes
    -0.80
    thren
    -0.79
     DIFFERENT
    -0.78
     sièges
    -0.78
    POSITIVE LOGITS
    BuildContext
    0.99
     collaborative
    0.86
     (
    0.84
     Отечественной
    0.83
     =>
    0.82
     all
    0.81
     only
    0.81
     context
    0.80
     Thomas
    0.79
     holistic
    0.79
    Activations Density 0.004%

    No Known Activations