© 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. 30534
    Prev
    Next
    INDEX
    Explanations

    clickable options, popup menus

    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
     jälkeen
    -0.78
     retirement
    -0.78
     SOT
    -0.77
    RadioButton
    -0.75
    次は
    -0.74
    قدر
    -0.73
    thermia
    -0.73
     Dura
    -0.72
    centering
    -0.71
    iquest
    -0.71
    POSITIVE LOGITS
     filtering
    0.80
    filtering
    0.79
     isOpen
    0.77
    osos
    0.74
    velocityY
    0.72
     Filtering
    0.72
     suggest
    0.71
     participan
    0.71
    Filtering
    0.71
    popup
    0.71
    Activations Density 0.043%

    No Known Activations