© 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. 95348
    Prev
    Next
    INDEX
    Explanations

    articles and stories

    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
    enação
    -1.06
    fgaben
    -1.03
    стрее
    -1.02
     for
    -1.00
    序列
    -0.95
    dientemente
    -0.91
    !
    -0.91
    要求
    -0.91
    ilo
    -0.90
    che
    -0.89
    POSITIVE LOGITS
     article
    2.05
     articles
    1.95
     newspapers
    1.57
     newspaper
    1.50
     about
    1.39
    この記事
    1.33
     газе
    1.32
    articles
    1.30
     artyku
    1.30
     estampado
    1.26
    Activations Density 0.078%

    No Known Activations