© 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. 22-GEMMASCOPE-RES-131K
    7. 95580
    Prev
    Next
    INDEX
    Explanations

    size and shape descriptors

    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
     resultaten
    -1.33
    ㍑
    -0.96
    livé
    -0.94
     Dermatologist
    -0.90
    Especificações
    -0.90
     sprüche
    -0.89
    Odkazy
    -0.88
    ]}{
    -0.88
     '
    -0.88
    }],
    -0.88
    POSITIVE LOGITS
     size
    0.99
    .
    0.81
    siano
    0.77
     volume
    0.76
     completes
    0.76
    В
    0.75
     www
    0.74
     (
    0.73
    size
    0.73
     open
    0.73
    Activations Density 0.115%

    No Known Activations