© 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. 49919
    Prev
    Next
    INDEX
    Explanations

    relations and normalization

    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
     interieur
    -0.74
    builtins
    -0.73
    ссиона
    -0.72
    lipop
    -0.69
     parfa
    -0.69
    nsec
    -0.69
    ($("#
    -0.68
    forcer
    -0.68
    initely
    -0.67
    äss
    -0.67
    POSITIVE LOGITS
     relations
    2.70
     normalization
    2.16
     Relations
    2.11
     normalize
    2.00
    Relations
    1.98
     normalized
    1.97
    relations
    1.95
    Normalization
    1.88
    normalization
    1.82
     relationships
    1.80
    Activations Density 0.036%

    No Known Activations