© 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. 76428
    Prev
    Next
    INDEX
    Explanations

    refinement

    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
     ngủ
    -0.70
    num
    -0.69
    _{
    -0.68
     recession
    -0.68
     unarmed
    -0.68
    linear
    -0.68
    sp
    -0.67
    Ser
    -0.66
    span
    -0.66
     Recons
    -0.65
    POSITIVE LOGITS
     refinement
    1.05
    Refinement
    0.98
    refine
    0.98
     refine
    0.96
     refined
    0.96
     refining
    0.95
    occup
    0.94
    refined
    0.94
     TLS
    0.89
     anisotropic
    0.89
    Activations Density 0.027%

    No Known Activations