© 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. 63745
    Prev
    Next
    INDEX
    Explanations

    game tile definitions

    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
     ideen
    -0.87
     jerawat
    -0.78
    getActiveSheet
    -0.77
     kering
    -0.77
    ajā
    -0.76
     kök
    -0.76
    📍
    -0.76
     radikal
    -0.75
     lasse
    -0.75
     suscit
    -0.75
    POSITIVE LOGITS
     door
    1.45
     water
    1.45
     exit
    1.17
     grass
    1.14
     stairs
    1.10
     gate
    1.10
     platforms
    1.05
     portal
    1.05
     flower
    1.04
     enemy
    1.04
    Activations Density 0.016%

    No Known Activations