© 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. 59823
    Prev
    Next
    INDEX
    Explanations

    stateful operators

    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
    ongan
    -0.69
     ACO
    -0.69
     februar
    -0.69
     VC
    -0.68
     коль
    -0.68
    cida
    -0.66
    engan
    -0.66
     Biggs
    -0.65
     decision
    -0.65
     동
    -0.64
    POSITIVE LOGITS
     operator
    1.09
     operators
    1.08
     OPERATOR
    1.05
     Operator
    1.02
     sink
    1.02
     Operators
    0.97
    sink
    0.96
    operator
    0.91
    operators
    0.90
    Operators
    0.88
    Activations Density 0.027%

    No Known Activations