© 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. 62955
    Prev
    Next
    INDEX
    Explanations

    platform adventure

    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
    cuda
    -0.94
    Blender
    -0.83
     awakeFromNib
    -0.80
    compass
    -0.76
     rudder
    -0.76
    zeiger
    -0.75
    geology
    -0.75
    freep
    -0.74
     hydrolysis
    -0.72
    stakes
    -0.71
    POSITIVE LOGITS
     platform
    3.11
     platforms
    2.94
    platform
    2.86
    Platform
    2.58
    platforms
    2.55
     Platform
    2.55
     Platforms
    2.44
    PLATFORM
    2.38
     plataformas
    2.36
    平台
    2.31
    Activations Density 0.048%

    No Known Activations