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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109468
    Prev
    Next
    INDEX
    Explanations

    game dev topics

    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
     chuẩn
    -0.82
     illimit
    -0.81
    DVD
    -0.80
    ⚾
    -0.77
    ⇌
    -0.77
     Segura
    -0.76
    mtp
    -0.75
    Movies
    -0.75
    cheidung
    -0.74
    babel
    -0.74
    POSITIVE LOGITS
     itch
    1.82
     Unity
    1.28
     IGF
    1.26
     indie
    1.23
     pygame
    1.21
     game
    1.16
     Indie
    1.16
    indie
    1.12
    itch
    1.10
     unity
    1.06
    Activations Density 0.068%

    No Known Activations