© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12369
    Prev
    Next
    INDEX
    Explanations

    date formatting and time utilities

    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
     pensó
    -1.49
     emprender
    -1.38
     軽量
    -1.16
     fortalecer
    -1.13
     aliviar
    -1.13
     inalámb
    -1.13
     consideró
    -1.10
     afrontar
    -1.08
     reconoció
    -1.08
     pensaba
    -1.08
    POSITIVE LOGITS
     febrero
    1.09
    úrg
    1.08
     time
    1.05
    zensionen
    1.04
    мне
    1.04
     输出
    1.03
    sprechend
    1.01
    Thesis
    1.00
    ÑOS
    1.00
     Mara
    0.99
    Activations Density 0.020%

    No Known Activations