© 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. 40308
    Prev
    Next
    INDEX
    Explanations

    placeholders followed by 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_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
     wobec
    -1.05
    εβ
    -0.93
     дорог
    -0.93
    論
    -0.93
    radiated
    -0.92
     kommunik
    -0.91
     rela
    -0.90
     maksimal
    -0.88
     akku
    -0.88
    AllowUser
    -0.88
    POSITIVE LOGITS
    ttää
    0.92
    Филь
    0.89
    hradun
    0.88
    bujete
    0.85
    內容簡介
    0.85
    カン
    0.85
     précisé
    0.84
    diğinde
    0.83
    ëren
    0.83
     Ihres
    0.82
    Activations Density 0.010%

    No Known Activations