© 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. 7266
    Prev
    Next
    INDEX
    Explanations

    creation and use

    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
    したのが
    -1.05
     какъ
    -1.01
     réforme
    -1.00
     няколко
    -0.99
     barva
    -0.99
     vooral
    -0.99
     refresher
    -0.98
     bojo
    -0.98
     récente
    -0.97
     obuv
    -0.97
    POSITIVE LOGITS
     creation
    3.66
    creation
    2.72
     use
    2.47
     removal
    2.47
     establishment
    2.42
     introduction
    2.23
     formation
    2.22
     issuance
    2.13
     completion
    2.09
     implementation
    2.06
    Activations Density 0.268%

    No Known Activations