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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70092
    Prev
    Next
    INDEX
    Explanations

    technical component types

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

    The neuron identifies key stems of technical compound terms—especially the first parts of hyphenated or multiword jargon (e.g. “code-” in “code-division,” “line” in “line-scan,” “packet-” in “packet-switched,” “block” in “block-level,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     on
    -1.63
    ®:
    -1.49
    '));
    
    -1.35
    markets
    -1.27
     novin
    -1.27
     that
    -1.26
    ch
    -1.26
    ТЬ
    -1.25
     facie
    -1.24
    omsday
    -1.23
    POSITIVE LOGITS
     入っ
    1.57
     our
    1.55
     unserem
    1.54
     Що
    1.46
     入り
    1.42
     нашего
    1.41
     более
    1.38
     gerçek
    1.37
     unseres
    1.37
    私たち
    1.36
    Activations Density 0.381%

    No Known Activations