© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41239
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives

    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_10/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
    我们
    -1.84
     Perſ
    -1.66
     ALSO
    -1.55
     másik
    -1.54
    他们
    -1.52
    matisch
    -1.47
                        
    -1.45
     también
    -1.42
     aussi
    -1.41
     elever
    -1.41
    POSITIVE LOGITS
     that
    2.13
     of
    1.84
     than
    1.70
     Of
    1.57
     it
    1.50
    それを
    1.41
     on
    1.41
     schließlich
    1.37
    est
    1.37
     complimented
    1.36
    Activations Density 0.701%

    No Known Activations