© 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. 57094
    Prev
    Next
    INDEX
    Explanations

    the list

    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
    õ
    -0.76
    ErrUnexpected
    -0.73
     averaging
    -0.71
     період
    -0.71
    array
    -0.69
     Karnataka
    -0.69
     Satz
    -0.69
    beelding
    -0.68
     assemblies
    -0.68
    固
    -0.67
    POSITIVE LOGITS
     Backbone
    1.01
    collection
    0.90
    Backbone
    0.88
     collection
    0.87
    CollectionView
    0.87
    Collection
    0.87
    Rendered
    0.79
    NYA
    0.79
    纽约
    0.79
    ベン
    0.79
    Activations Density 0.013%

    No Known Activations