© 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. 33419
    Prev
    Next
    INDEX
    Explanations

    program data types and structures

    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
     methodName
    -0.75
     affirme
    -0.75
     λά
    -0.74
     哪些
    -0.73
     cantora
    -0.71
    屬
    -0.70
     intramuscular
    -0.70
    üsse
    -0.70
     GRADUATE
    -0.69
     erhö
    -0.69
    POSITIVE LOGITS
     struct
    1.27
    record
    1.27
    Record
    1.25
     RECORD
    1.25
     record
    1.24
    RECORD
    1.23
     type
    1.20
     class
    1.20
     classes
    1.18
     Record
    1.12
    Activations Density 0.190%

    No Known Activations