© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59352
    Prev
    Next
    INDEX
    Explanations

    drop item

    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
    ficas
    -0.94
    Customers
    -0.79
     Customers
    -0.76
    AccessFile
    -0.75
     getElement
    -0.74
     customers
    -0.72
     преиму
    -0.69
     crucified
    -0.69
    setDisable
    -0.68
     أبي
    -0.67
    POSITIVE LOGITS
     item
    1.68
     inventory
    1.55
     items
    1.55
    ItemStack
    1.52
     stack
    1.48
    stack
    1.42
     stacking
    1.33
    物品
    1.31
    アイテム
    1.30
     ItemStack
    1.30
    Activations Density 0.014%

    No Known Activations