© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47398
    Prev
    Next
    INDEX
    Explanations

    command prefix or dates

    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
    這
    -0.90
    演員
    -0.87
    írit
    -0.85
    本日は
    -0.81
     deaktiviert
    -0.79
     Hawke
    -0.78
    likes
    -0.77
    سپ
    -0.75
     genoemd
    -0.75
    sworth
    -0.74
    POSITIVE LOGITS
     commands
    2.11
     command
    2.09
    commands
    1.64
    command
    1.64
     Commands
    1.54
     Command
    1.52
    Commands
    1.48
     COMMAND
    1.48
     prefix
    1.44
    Command
    1.39
    Activations Density 0.017%

    No Known Activations