© 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. 34-GEMMASCOPE-RES-131K
    7. 87173
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

    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_34/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
     köt
    -0.97
    🪒
    -0.90
    tikai
    -0.90
     bénéfice
    -0.88
    ;=
    -0.87
    fruta
    -0.86
     lendemain
    -0.86
    вей
    -0.85
    Several
    -0.85
     parfaite
    -0.84
    POSITIVE LOGITS
     sort
    1.03
    找不到
    0.90
     for
    0.90
    好みの
    0.87
     length
    0.83
    都是在
    0.82
     길
    0.82
     derselben
    0.81
     confirm
    0.81
     perform
    0.81
    Activations Density 0.027%

    No Known Activations