© 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. 2772
    Prev
    Next
    INDEX
    Explanations

    element belongs to set

    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
     Daß
    -0.84
     Ebenso
    -0.84
    ન્
    -0.81
     addressee
    -0.79
    чники
    -0.79
    trás
    -0.78
     dietro
    -0.77
     rundt
    -0.76
     Савезне
    -0.75
    禧
    -0.75
    POSITIVE LOGITS
     ∈
    2.81
     in
    2.75
    ∈
    2.53
     belongs
    1.95
     belong
    1.91
     belonging
    1.83
    属于
    1.65
    屬於
    1.64
     thuộc
    1.62
     belonged
    1.54
    Activations Density 0.059%

    No Known Activations