© 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. 116911
    Prev
    Next
    INDEX
    Explanations

    not yet completed or determined

    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
    already
    -1.43
     पहले
    -1.28
     already
    -1.28
     henceforth
    -1.25
     eventually
    -1.24
     never
    -1.20
     initially
    -1.20
     désormais
    -1.18
    eventually
    -1.12
    never
    -1.11
    POSITIVE LOGITS
     fully
    1.75
     nor
    1.47
    正式
    1.40
    完全
    1.34
     yet
    1.29
     even
    1.26
    有任何
    1.23
     Fully
    1.22
     sepenuhnya
    1.21
     any
    1.20
    Activations Density 0.048%

    No Known Activations