© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23458
    Prev
    Next
    INDEX
    Explanations

    data structures and types

    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
     Collections
    -0.81
     lists
    -0.81
    istle
    -0.77
     dataTable
    -0.77
     entries
    -0.77
    lohn
    -0.77
     item
    -0.76
    郫
    -0.76
     string
    -0.75
     enfrenta
    -0.75
    POSITIVE LOGITS
    uttgart
    0.91
    ᚕ
    0.79
    λευ
    0.78
     java
    0.76
     delante
    0.75
    手に入
    0.75
    Bag
    0.73
    ówczas
    0.72
    dding
    0.69
    entos
    0.69
    Activations Density 0.029%

    No Known Activations