© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26225
    Prev
    Next
    INDEX
    Explanations

    similarity and comparison

    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_22/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
    Composición
    -0.94
     зви
    -0.85
    productivity
    -0.85
    individ
    -0.84
    constra
    -0.83
    [&
    -0.83
    adjustment
    -0.82
     médic
    -0.82
    interference
    -0.81
    لاء
    -0.80
    POSITIVE LOGITS
     similares
    1.10
     similar
    1.09
     likes
    1.01
     podob
    0.99
    一样
    0.99
     similarly
    0.96
    一樣
    0.95
     benzer
    0.94
     links
    0.94
     themes
    0.93
    Activations Density 0.043%

    No Known Activations