© 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. 59738
    Prev
    Next
    INDEX
    Explanations

    Martian and Mars related terms

    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
     Oceanic
    -0.82
     meats
    -0.81
     shatter
    -0.79
     oceanic
    -0.78
    oyle
    -0.73
     зло
    -0.72
     Bach
    -0.71
    Milestone
    -0.69
     ocean
    -0.68
     oils
    -0.68
    POSITIVE LOGITS
     Martian
    1.35
     Mars
    1.07
    Mars
    1.02
    vins
    0.93
     MARS
    0.90
     мар
    0.90
    rpura
    0.84
     Viking
    0.82
     denaro
    0.82
     Мар
    0.81
    Activations Density 0.013%

    No Known Activations