© 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. 84395
    Prev
    Next
    INDEX
    Explanations

    all followed by a noun

    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
    臜
    -1.43
    вшим
    -1.41
     alcune
    -1.39
     certaines
    -1.38
    跄
    -1.37
     is
    -1.35
    Guides
    -1.32
     konkret
    -1.32
    楽しんで
    -1.31
    앓
    -1.29
    POSITIVE LOGITS
     encompassing
    1.90
    _
    1.77
     you
    1.77
     There
    1.66
    l
    1.63
    日で
    1.63
     categorized
    1.61
    始まり
    1.57
    D
    1.52
     Everything
    1.51
    Activations Density 0.009%

    No Known Activations