© 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. 33252
    Prev
    Next
    INDEX
    Explanations

    news and media outlets

    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
     from
    -1.02
    便宜
    -0.90
     until
    -0.89
     still
    -0.84
    夷
    -0.82
    烟
    -0.79
     untill
    -0.79
    臨
    -0.77
    didSet
    -0.76
    Infor
    -0.76
    POSITIVE LOGITS
     numerous
    1.40
     Huffington
    1.38
     여러
    1.23
     various
    1.21
     national
    1.15
     CNN
    1.10
    Huff
    1.06
     apareció
    1.05
     Yahoo
    1.03
     several
    1.02
    Activations Density 0.039%

    No Known Activations