© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109297
    Prev
    Next
    INDEX
    Explanations

    mathematics and names

    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
    UIAlert
    -0.80
     rép
    -0.73
     chert
    -0.73
    mods
    -0.68
    ningarna
    -0.68
    Solución
    -0.68
    culadora
    -0.68
    begriff
    -0.67
    bound
    -0.67
    latego
    -0.67
    POSITIVE LOGITS
     avoidance
    0.90
     Dumont
    0.87
     Deccan
    0.85
    insertion
    0.84
    melde
    0.81
     Statistics
    0.80
    sortable
    0.77
     parking
    0.77
    statistics
    0.76
    Insertion
    0.76
    Activations Density 0.058%

    No Known Activations