© 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. 11219
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
    })^
    -1.21
     and
    -1.15
    Who
    -0.93
    |^{
    -0.90
    >(&
    -0.89
    masını
    -0.88
    rdom
    -0.87
     milhares
    -0.87
    dzi
    -0.85
    |^
    -0.85
    POSITIVE LOGITS
     your
    1.02
     în
    0.93
     logica
    0.92
    RemoteException
    0.90
     composés
    0.90
     pengusaha
    0.88
    양
    0.88
    у
    0.87
     マイク
    0.85
    ag
    0.85
    Activations Density 0.012%

    No Known Activations