© 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. 10-GEMMASCOPE-RES-131K
    7. 102430
    Prev
    Next
    INDEX
    Explanations

    JavaScript DOM APIs and CSS flexbox

    np_acts-logits-general · gemini-2.5-flash-lite

    JavaScript/programming code, particularly object property access and method calls using dot notation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    NEM
    -1.42
    égio
    -1.30
     canzoni
    -1.23
     Zoltán
    -1.23
     condam
    -1.22
     awakeFromNib
    -1.22
    fähig
    -1.21
     ceremonia
    -1.20
    cijas
    -1.20
    helfen
    -1.20
    POSITIVE LOGITS
     latter
    1.31
    </strong>
    1.31
     current
    1.22
     or
    1.22
     its
    1.20
    3
    1.17
    誰か
    1.17
    還會
    1.13
     decorativo
    1.11
    說的
    1.10
    Activations Density 0.077%

    No Known Activations