© 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. 66421
    Prev
    Next
    INDEX
    Explanations

    approximations and conditions

    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
    thâu
    -0.97
    مقدمه
    -0.95
    ggiare
    -0.94
    ́
    -0.92
    瑞士
    -0.89
     makinesi
    -0.89
     such
    -0.89
    第一章
    -0.89
     hängt
    -0.88
     löst
    -0.88
    POSITIVE LOGITS
     would
    1.59
     about
    1.42
     roughly
    1.41
     approximately
    1.20
     примерно
    1.13
     تقری
    1.11
     somit
    1.05
     then
    1.05
    pherds
    1.00
    roughly
    0.97
    Activations Density 0.031%

    No Known Activations