© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106897
    Prev
    Next
    INDEX
    Explanations

    healthy controls and age

    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
    oulli
    -0.86
    諡
    -0.84
    letoe
    -0.79
     Moun
    -0.79
     hymns
    -0.77
    vil
    -0.76
     kimi
    -0.74
     gladi
    -0.73
    针
    -0.73
     игроков
    -0.72
    POSITIVE LOGITS
     healthy
    2.41
     controls
    2.17
    controls
    1.88
     control
    1.84
    healthy
    1.83
     Healthy
    1.79
     Controls
    1.75
    Healthy
    1.69
    Controls
    1.56
     age
    1.52
    Activations Density 0.396%

    No Known Activations