© 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. 67684
    Prev
    Next
    INDEX
    Explanations

    words ending in -an

    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
     sentire
    -2.66
     giudi
    -2.66
     voelen
    -2.64
     ส์
    -2.64
    ﮑ
    -2.59
     innamor
    -2.58
    髕
    -2.55
    噚
    -2.52
    
    -2.50
     trattato
    -2.47
    POSITIVE LOGITS
    D
    3.08
    -
    2.97
    A
    2.80
    `
    2.72
    U
    2.69
    </h2>
    2.52
    E
    2.50
    -"
    2.47
    #
    2.42
    =
    2.39
    Activations Density 0.120%

    No Known Activations