© 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. 81474
    Prev
    Next
    INDEX
    Explanations

    time and now

    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
     lifelong
    -1.14
     further
    -1.01
    ときの
    -0.94
    了一個
    -0.92
     momentary
    -0.92
     damals
    -0.89
    ريعة
    -0.89
     nuovamente
    -0.88
    了一下
    -0.88
    をした
    -0.88
    POSITIVE LOGITS
     already
    1.50
     ago
    1.44
     now
    1.42
    Already
    1.37
     ormai
    1.30
    already
    1.23
     уже
    1.20
    ènements
    1.19
     Already
    1.17
     вже
    1.15
    Activations Density 0.031%

    No Known Activations