© 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. 22-GEMMASCOPE-RES-131K
    4. 38777
    Prev
    Next
    INDEX
    Explanations

    elderly, solitary, active individuals

    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
    ebly
    -1.41
     suspe
    -1.32
    '):
    
    -1.29
    .
    
    -1.24
     tudi
    -1.23
    ':
    
    -1.22
    橈
    -1.19
     otros
    -1.15
    }),
    
    -1.12
     apesar
    -1.12
    POSITIVE LOGITS
     ones
    1.73
     people
    1.57
     countries
    1.49
     cannot
    1.46
     individuals
    1.45
     and
    1.39
     companies
    1.38
    izing
    1.27
     चीज़
    1.26
     llavero
    1.24
    Activations Density 0.100%

    No Known Activations