© 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. 93544
    Prev
    Next
    INDEX
    Explanations

    stroller

    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
    Faker
    -0.78
    房間
    -0.76
    tský
    -0.76
    textField
    -0.75
    房间
    -0.75
     drywall
    -0.71
    conectar
    -0.70
    ченным
    -0.69
     Tolkien
    -0.69
    ますが
    -0.69
    POSITIVE LOGITS
     stroller
    3.03
     pram
    2.30
     коля
    1.88
     buggy
    1.75
     push
    1.63
     Pram
    1.61
    Push
    1.59
     baby
    1.48
     Push
    1.42
    push
    1.41
    Activations Density 0.024%

    No Known Activations