© 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. 79132
    Prev
    Next
    INDEX
    Explanations

    game development and platforms

    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
    onNext
    -0.86
     today
    -0.84
     Reichs
    -0.80
     мечта
    -0.79
     ogn
    -0.78
     ofc
    -0.77
     book
    -0.76
    芮
    -0.76
     nM
    -0.75
     covid
    -0.74
    POSITIVE LOGITS
    Developer
    1.08
     retrô
    1.02
    SOURCE
    1.02
     developer
    1.00
     gameplay
    0.99
    攥
    0.99
    platform
    0.98
     beelden
    0.98
     ilustracji
    0.98
     खेल
    0.97
    Activations Density 0.014%

    No Known Activations